Fixed: Neo4j queries now respect the configured database
Neo4jDriver.execute_query() previously ignored the driver's database setting and ran all queries (including searches) against the server's home database, while session-based writes used the configured one (#1481, #851, #798). Queries are now correctly routed to the configured database, defaulting to neo4j. A per-call override is also supported via execute_query(..., database_="name").

⚠️ Behavior change for existing deployments:

WHO IS AFFECTED: This only impacts self-hosted Neo4j Enterprise deployments (multi-database support is an Enterprise feature) where the database parameter was manually set to something other than neo4j in the Graphiti client, or where the server's default database was renamed. If you run a standard Neo4j setup with the default neo4j database, no action is needed.

If your server's home database is not named neo4j and you don't pass database to the driver, queries now target neo4j instead of your home database — pass your database name explicitly to keep the old behavior.
If you configured a custom database, reads now correctly target it. Data previously written via execute_query may reside in your home database and may need to be migrated.

What's Changed

• docs: remove Discord mentions, use GitHub for discussion by @jackaldenryan in #1708
• feat: add source_node_uuid, target_node_uuid, and episodes to FactResult model and edge processing by @mehulp93 in #1750
• fix edge cross-encoder shortlist via balanced merge (#1642) by @mehulp93 in #1754
• Remove Claude PR triage workflow by @mehulp93 in #1788
• fix(attributes): preserve prior node attributes when no entity type applies by @yatharth-anand-2410 in #1764
• Reframe README as a temporal knowledge graph framework by @danielchalef in #1801
• fix(neo4j): route queries to the configured database by @mehulp93 in #1814
• Bump graphiti-core to 0.30.0 by @prasmussen15 in #1818

New Contributors

• @mehulp93 made their first contribution in #1750
• @yatharth-anand-2410 made their first contribution in #1764

Full Changelog: v0.29.3...v0.30.0

What's Changed

• Allow Edge extraction to keep discovered edge labels by @danielchalef in https://github.com/getzep/graphiti/pull/950

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre4...v0.30.0pre5

What's Changed

• fix: Add edge type validation based on node labels by @danielchalef in https://github.com/getzep/graphiti/pull/948

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre3...v0.30.0pre4

What's Changed

• Improve node dedup prompts by @danielchalef in https://github.com/getzep/graphiti/pull/942
• bump 0.30.0pre3 by @danielchalef in https://github.com/getzep/graphiti/pull/946

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre2...v0.30.0pre3

What's Changed

• Fix index out of range errors in LLM deduplication responses by @danielchalef in https://github.com/getzep/graphiti/pull/939
• chore: Bump version by @paul-paliychuk in https://github.com/getzep/graphiti/pull/940

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre1...v0.30.0pre2

What's Changed

• Refactor batch deduplication logic to enhance node resolution and track duplicate pairs (#929) by @danielchalef in https://github.com/getzep/graphiti/pull/936
• Update pyproject.toml to 0.30.0pre1 by @danielchalef in https://github.com/getzep/graphiti/pull/938

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre0...v0.30.0pre1

What's Changed

• Improve node/edge deduplication w/ deterministic matching, LLM fallbacks by @danielchalef in https://github.com/getzep/graphiti/pull/929

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre6...v0.30.0pre0

What's Changed

• chore(deps-dev): update redis requirement from <8 to <9 by @dependabot[bot] in #1561
• chore(deps-dev): update azure-identity requirement from >=1.21.0 to >=1.25.3 in /mcp_server by @dependabot[bot] in #1562
• chore(deps-dev): update google-genai requirement from >=1.72.0 to >=2.8.0 in /mcp_server by @dependabot[bot] in #1563
• chore(deps): update graphiti-core requirement from >=0.29.1 to >=0.29.2 in /mcp_server by @dependabot[bot] in #1565
• chore(deps-dev): update pytest-asyncio requirement from >=1.3.0 to >=1.4.0 in /mcp_server by @dependabot[bot] in #1566
• chore(deps): update openai requirement from >=1.91.0 to >=2.41.0 in /mcp_server by @dependabot[bot] in #1564
• ci(server): live end-to-end regression test + PR check by @danielchalef in #1560
• ci: harden exit-5 handling in the live-test workflows (MCP backport + diagnostics) by @danielchalef in #1567
• chore(deps): fix all Dependabot security alerts by @danielchalef in #1599
• fix(docker): drop procps so the combined FalkorDB image builds on trixie by @irresi in #1628
• fix(docker): avoid host PATH interpolation by @dpersek in #1630
• fix(falkordb): short-circuit fulltext query when every token was a stopword by @aasc77 in #1590
• fix(mcp): preserve FalkorDB URI username by @he-yufeng in #1530
• fix: handle backtick tokens and empty queries in FalkorDB fulltext search by @Maanik23 in #1475
• fix(falkordb): route single group_id search to the matching graph by @Solaris-star in #1670
• docs: note Zep's proprietary Context Graph Engine in README by @jackaldenryan in #1665
• docs: add Cursor Cloud dev environment setup instructions by @danielchalef in #1677
• disable Claude GitHub Actions workflows by @danielchalef in #1678
• fix(falkordb): route namespace/ops get_by_group_ids reads to the group's graph by @spencer2211 in #1675
• fix(mcp): search returns empty results after container restart by @husniadil in #1105
• fix: capture init task ref + cancel on close for Neo4jDriver and FalkorDriver by @nandanadileep in #1636
• fix(mcp): configure cross-encoder from providers instead of hardcoded OpenAI by @winklemad in #1637
• fix(communities): scope remove_communities to the group_ids being rebuilt by @Saltasm in #1658
• fix(mcp): expose generic structured output mode by @xiaoyaner0201 in #1619
• fix(edges): return reference_time in entity edge read query by @ly-wang19 in #1605
• fix(search): consume bfs relationship hits directly in edge_bfs_search by @kramerica-inc-dev in #1653
• Add Socket Firewall enforcement to CI and releases by @paul-paliychuk in #1681
• fix: preserve relationship direction in get_by_node_uuid and BFS edge search by @6or7 in #1663
• Consolidate overlapping backend fixes by @prasmussen15 in #1695
• Bump graphiti-core to 0.29.3 by @prasmussen15 in #1696

New Contributors

• @irresi made their first contribution in #1628
• @dpersek made their first contribution in #1630
• @aasc77 made their first contribution in #1590
• @Solaris-star made their first contribution in #1670
• @spencer2211 made their first contribution in #1675
• @husniadil made their first contribution in #1105
• @nandanadileep made their first contribution in #1636
• @winklemad made their first contribution in #1637
• @Saltasm made their first contribution in #1658
• @xiaoyaner0201 made their first contribution in #1619
• @ly-wang19 made their first contribution in #1605
• @kramerica-inc-dev made their first contribution in #1653
• @6or7 made their first contribution in #1663

Full Changelog: v0.29.2...v0.29.3

What's Changed

• fix(deps): resolve all open Dependabot alerts in uv.lock files by @jackaldenryan in #1528
• fix(falkor): strip nul bytes from parameters by @he-yufeng in #1531
• fix: FalkorDB profile failing to start in docker-compose by @Naseem77 in #1126
• fix(docker): align FalkorDB compose service port with container by @prasmussen15 in #1532
• Fix Ollama/OpenAI-compatible provider support by @Naseem77 in #1146
• fix(mcp): extend model env overrides to all configs + test provider routing by @prasmussen15 in #1535
• Add Support falkordblite - FalkorDB embedded version by @galshubeli in #1125
• fix(falkordblite): make embedded install work (pin redis<8) + example cleanup by @prasmussen15 in #1536
• ci: use IPv4 (127.0.0.1) for FalkorDB/Neo4j waits in integration tests by @danielchalef in #1538
• ci(cla): authenticate CLA Assistant with a GitHub App token, drop the PAT by @danielchalef in #1541
• ci: fix (id-token) and harden Claude review/triage workflows by @danielchalef in #1540
• ci: make Claude review work on Opus 4.8 (github_token + action bump) + re-add synchronize by @danielchalef in #1542
• ci: bump claude-code-action to v1.0.139 (agent SDK that recognizes Opus 4.8) by @danielchalef in #1543
• ci: make Claude review post on Opus 4.8 (anti-suppress prompt + read-only tools) by @danielchalef in #1544
• ci: allowlist the github_comment tool so Claude review actually posts by @danielchalef in #1545
• ci: use track_progress for Claude PR review (the actual comment mechanism) by @danielchalef in #1546
• fix(llm): default OpenAIGenericClient to json_schema with json_object fallback by @danielchalef in #1537
• deprecate(kuzu): mark Kuzu deprecated; drop from default test matrix by @danielchalef in #1548
• ci: run ruff lint/format on fork PRs via privilege-stripped pull_request_target by @danielchalef in #1550
• feat(llm): default to gpt-5.5 with model-tied reasoning effort by @danielchalef in #1551
• chore(mcp): modernize dependencies, MCP SDK, and default models by @danielchalef in #1552
• feat(mcp): core-parity — bi-temporal, sagas, communities, filters, triplets, custom types by @danielchalef in #1553
• test(mcp): live end-to-end FalkorDB suite + CI workflow (gpt-5.5) by @danielchalef in #1557
• ci(mcp): treat pytest exit-5 (suite self-skipped) as success by @danielchalef in #1559
• fix: apply --host and --port CLI flags in apply_cli_overrides by @Maanik23 in #1376
• feat(mcp): accept a scalar group_id on the read tools by @danielchalef in #1558
• chore(deps-dev): update faker requirement from >=37.12.0 to >=40.21.0 in /mcp_server by @dependabot[bot] in #1447
• chore(deps-dev): update ruff requirement from >=0.7.1 to >=0.15.16 in /mcp_server by @dependabot[bot] in #1446
• chore(deps): update pyyaml requirement from >=6.0 to >=6.0.3 in /mcp_server by @dependabot[bot] in #1445
• chore(deps-dev): update anthropic requirement from >=0.49.0 to >=0.107.1 in /mcp_server by @dependabot[bot] in #1449
• fix(falkordb): make default group_id valid and escape it for RediSearch by @prasmussen15 in #1549

New Contributors

• @he-yufeng made their first contribution in #1531
• @Maanik23 made their first contribution in #1376

Full Changelog: v0.29.1...v0.29.2

Patch release covering quality and reliability improvements landed since 0.29.0.

Extraction quality

Attribute-hallucination guards (#1498) — addresses a customer report of up to 9KB of LLM meta-reasoning landing in entity attribute fields (e.g. phones,
industry). The LLM was dumping internal deliberation and echoing schema description text back into values. Three layered defenses:

1. Prompt-level: extract_attributes prompts for both nodes and edges now have hard rules forbidding parenthetical reasoning, deliberative phrases, candidate
   alternatives, schema-description echoes, and null/N/A sentence stand-ins. Includes positive/negative examples.
2. Combined-extraction prompt: new OUTPUT DISCIPLINE block closes the "topic-as-Person" failure mode (full-sentence entity names) and pre-empts reasoning leaks
   into fact text and relation_type.
3. Provider-level preamble: a shared _apply_attribute_extraction_preamble on LLMClient mutates the system message across OpenAI, Anthropic, Gemini, and GLiNER2
   so the "field descriptions are format specs, not values" instruction reaches every provider regardless of how structured output is wired. Sentinel-based
   idempotency.

Structural backstop — cap_string_attributes: drops any string attribute >250 chars before it reaches the graph. Configurable per-field via Pydantic
Field(max_length=...) or globally via GRAPHITI_ATTRIBUTE_MAX_LENGTH. Also handles list[str] (per-item + aggregate cap of max_len * 8). Required-field carve-out
retains the value with a louder WARNING rather than dropping (avoids ValidationError-ing the whole entity). Edge writes use scoped merge for over-cap drops only
— fields the LLM legitimately omitted still clear. group_id flows to the log line for tenant correlation.

Combined-extraction entity & edge precision (#1498) — targets six classes of low-quality entities (multi-choice fragments, clock times, quantities, coordinates,
imperative tip phrases, slogans) plus two systematic edge regressions (location-fragmentation through scenery intermediaries, dropped multi-episode setup
facts).

• ENTITY RULE 6 expanded into 8 sub-bullets covering the skip classes; ENTITY RULE 9 added for didactic / tutorial scaffolding.
• FACT RULE 4 strengthened around narrative announcements, forward commitments, plans, and emotional setup in conversational episodes; FACT RULE 8 added
  requiring direct speaker-to-target edges over fragmenting through scenery intermediaries.
• Negative-examples block (A–G) added with paired source-and-extraction guidance per class.

Locomo 500-example eval (prompt change only):

• Entity F1: 0.674 (flat); precision −0.028, recall +0.025
• Edge volume: +7.7% over baseline; gold-edge recall +0.9pp
• Fact-text Jaccard on matched edges: 0.341 → 0.381
• Targeted entity classes on LME-derivative sample: quantities −93%, imperative tips −40%

Saga summarization

Episode-time watermarks for sagas (#1498) — saga (thread summary) timestamps now reflect originating-episode time rather than wall-clock time. SagaNode now
carries two deliberately distinct watermarks:

• last_summarized_at (wall-clock) — the filter watermark. summarize_saga picks up any episode whose created_at > this value. Wall-clock + created_at comparison
  keeps backfilled episodes reachable on the next run.
• last_summarized_episode_valid_at (episode time) — the temporal watermark. Max valid_at across episodes covered by the current summary; advances monotonically.
  Public/temporal consumers ("how recent is this summary's content in event-time?") should use this field.

saga_get_episode_contents now returns list[(content, valid_at)] tuples so callers can compute the watermark. _get_or_create_saga renames now → created_at;
callers pass the episode's valid_at so a newly minted saga's created_at matches the episode that produced it.

Docker / packaging

• fix(mcp): install MCP provider extras in Docker images (#1461)
• fix(docker): mount FalkorDB volume to actual data path (#1462) — earlier mount path didn't match FalkorDB's data directory, so data wasn't actually persisted
  across container restarts.
• chore(deps): bump uv group across 2 directories (#1473) — jupyterlab 4.5.7, plus indirect updates to jupyter-server 2.18.0, mistune 3.2.1, python-multipart
  0.0.27.

Docs

• docs(graphiti): drop stale add_episode_bulk warning (#1476) — removed an outdated docstring that warned the bulk path skipped edge invalidation and date
  extraction. That hasn't been true since the bulk pipeline was rewritten to share per-episode primitives (resolve_extracted_edges, extract_edges both run on the
  bulk path).

What's Changed

• docs(graphiti): drop stale add_episode_bulk edge-invalidation/date-extraction note by @prasmussen15 in #1476
• Bump the uv group across 2 directories with 4 updates by @dependabot[bot] in #1473
• fix(docker): mount FalkorDB volume to actual data path by @fengfeng-zi in #1462
• fix: install MCP provider extras in Docker images by @fengfeng-zi in #1461
• Forward-port: attribute-hallucination guards, combined-extraction precision, saga episode-time watermarks by @prasmussen15 in #1498
• Bump graphiti-core version to 0.29.1 by @prasmussen15 in #1499

New Contributors

• @fengfeng-zi made their first contribution in #1462

Full Changelog: v0.29.0...v0.29.1

Release Notes — graphiti-core 0.29.0

Summary

0.29.0 is the first of two releases focused on making ingestion meaningfully cheaper and the search pipeline easier to evolve. The headline changes:

Cheaper ingestion. A new combined node + edge extraction path lets a single LLM call cover what previously took two, and node/edge extraction can now batch multiple episodes into one prompt. Timestamp resolution (valid_at / invalid_at) has also been split into its own step so it doesn't compete with structural fact extraction. Search pipeline rework. A large internal restructure of graphiti_core/search/search.py lays the groundwork for upcoming search and reranker changes — no public API changes, but tracing coverage is much improved. New saga abstraction. A summarize_saga(saga_id) API on Graphiti, backed by SagaNode and a refreshed prompt, gives a first-class way to roll up multi-episode narratives. Quality-of-life. A fact_triple episode type, episode_metadata for filtering, safer attribute merging that no longer clobbers first-class fields, and a podcast example that runs against an embedded FalkorDB with no external DB. How this affects developers

Defaults are unchanged. Combined extraction is opt-in via use_combined_extraction=True on extract_nodes_and_edges_bulk. Existing ingestion code keeps working as-is. Episode indices are now 0-based. If you parse [Episode N] headers or rely on episode_indices from extraction results, update your offsets accordingly. Kuzu users — schema migration required. RelatesToNode_ now expects a reference_time TIMESTAMP column. New databases get it automatically; existing stores need a one-time ALTER TABLE RelatesToNode_ ADD reference_time TIMESTAMP. Custom attributes are now safer to set. Attribute dicts on nodes/edges no longer overwrite first-class fields (uuid, group_id, created_at, timestamps). If you were depending on that overwrite behavior, you'll need to set those fields directly. New public surface to know about: Graphiti.summarize_saga(saga_id), the fact_triple episode type, and EpisodicNode.episode_metadata for custom filtering keys. Highlights

Efficiency: fewer, smarter LLM calls during ingestion

Combined node + edge extraction (feature-flagged). A single LLM call can now produce both nodes and edges for an episode. Pass use_combined_extraction=True to extract_nodes_and_edges_bulk to opt in; default behavior is unchanged. Backed by a new prompts/extract_nodes_and_edges.py and utils/maintenance/combined_extraction.py. Multi-episode batched extraction. _extract_and_resolve_nodes and extract_edges now accept a list of episodes, build a shared prompt with [Episode N] headers (new concatenate_episodes helper), and attach episode_indices to each extracted node/edge so callers can map results back to their source episode. Decoupled timestamp resolution. New extract_timestamps / extract_timestamps_batch prompts let valid_at / invalid_at be resolved in a dedicated post-extraction step, so structural fact extraction is no longer entangled with date parsing. Architecture

Search pipeline rework. Major restructure of graphiti_core/search/search.py (~1k lines changed) and new tracing test coverage, paving the way for upcoming search/reranker changes. Sagas. New summarize_saga(saga_id) API on Graphiti, plus a refreshed summarize_sagas prompt and supporting helpers (saga_get_previous_episode_uuid, saga_get_episode_contents). fact_triple episode type and an episode_metadata dict on EpisodicNode for customer-defined filtering keys. Safer attribute merging on edges and nodes — first-class fields (uuid, group_id, created_at, timestamps) are no longer overwritten when an attribute dict happens to contain a matching key. reference_time preserved through bulk edge save, and added as a column on the Kuzu RelatesToNode schema. Existing Kuzu users may need a one-time ALTER TABLE RelatesToNode ADD reference_time TIMESTAMP. Prompt refinements

Dedup (nodes & edges): tightened scope, looser two-entity rule in the combined extraction path. Fact extraction: detail-preservation rule, broader entity capture for qualified objects. Refreshed summarize_sagas prompt. Examples / DX

examples/podcast/podcast_runner.py now runs against an embedded FalkorDB (falkordblite) with no external database, and exercises edge + node hybrid search post-ingest. Notable internal changes

Driver tweaks in graph_operations.py and record_parsers.py. Episode indexing is now 0-based (was 1-based in the first iteration of multi-episode extraction). pytest bumped to 9.0.3 in server/ and mcp_server/. Lockfile and dependency refreshes (uv group, voyageai, groq, google-genai, uvicorn, pyright, pytest-asyncio). Coming next

The next release will continue this architectural track — expect the combined extraction path to graduate toward the default ingestion mode, additional batching across edge resolution and dedup, and follow-on search-pipeline changes building on the rework that landed here.

What's Changed

• chore: regenerate lockfiles to drop diskcache by @prasmussen15 in https://github.com/getzep/graphiti/pull/1244
• fix: replace edge name with uuid in debug log by @prasmussen15 in https://github.com/getzep/graphiti/pull/1261
• chore: update Docker images to graphiti-core 0.28.1 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1292
• feat: Add GLiNER2 hybrid LLM client by @danielchalef in https://github.com/getzep/graphiti/pull/1284
• Refresh README content and fix image refs by @danielchalef in https://github.com/getzep/graphiti/pull/1313
• Restore README title and subtitle by @danielchalef in https://github.com/getzep/graphiti/pull/1314
• Harden search filters against Cypher injection by @danielchalef in https://github.com/getzep/graphiti/pull/1312

Full Changelog: https://github.com/getzep/graphiti/compare/v0.28.1...v0.28.2

What's Changed

• fix: extract custom edge attributes on first episode ingestion by @prasmussen15 in https://github.com/getzep/graphiti/pull/1242
• fix: replace diskcache with sqlite-based cache to resolve CVE by @jackaldenryan in https://github.com/getzep/graphiti/pull/1238
• chore: bump version to 0.28.1 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1243

Full Changelog: https://github.com/getzep/graphiti/compare/v0.28.0...v0.28.1

What's Changed

• feat: simplify extraction pipeline and add batch entity summarization by @prasmussen15 in https://github.com/getzep/graphiti/pull/1224
• chore(deps): update dependencies to fix dependabot alerts by @jackaldenryan in https://github.com/getzep/graphiti/pull/1225
• feat: driver operations architecture redesign by @prasmussen15 in https://github.com/getzep/graphiti/pull/1232
• Bump graphiti-core[falkordb] from 0.26.3 to 0.27.1 in /mcp_server by @dependabot[bot] in https://github.com/getzep/graphiti/pull/1231
• feat: implement Neptune and Kuzu driver operations by @prasmussen15 in https://github.com/getzep/graphiti/pull/1235
• chore: bump version to 0.28.0 and document graph driver architecture by @prasmussen15 in https://github.com/getzep/graphiti/pull/1236
• fix: remove PII from log messages by @prasmussen15 in https://github.com/getzep/graphiti/pull/1237

Full Changelog: https://github.com/getzep/graphiti/compare/v0.27.1...v0.28.0

What's Changed

• feat: simplify extraction pipeline and add batch entity summarization by @prasmussen15 in https://github.com/getzep/graphiti/pull/1224

Full Changelog: https://github.com/getzep/graphiti/compare/v0.27.1...v0.27.2pre1

What's Changed

• fix(summary): exclude duplicate edges from node summary generation by @prasmussen15 in https://github.com/getzep/graphiti/pull/1223

Full Changelog: https://github.com/getzep/graphiti/compare/v0.27.0...v0.27.1

What's Changed

• Add extracted edge facts to entity summaries by @prasmussen15 in https://github.com/getzep/graphiti/pull/1182
• Fix dependabot security vulnerabilities by @danielchalef in https://github.com/getzep/graphiti/pull/1184
• Revert "Fix dependabot security vulnerabilities" by @danielchalef in https://github.com/getzep/graphiti/pull/1185
• Pin mcp_server to graphiti-core 0.26.3 by @danielchalef in https://github.com/getzep/graphiti/pull/1186
• Update manual code review workflow to use claude-opus-4-5-20251101 by @danielchalef in https://github.com/getzep/graphiti/pull/1189
• Refactor prompt system for efficiency and clarity by @prasmussen15 in https://github.com/getzep/graphiti/pull/1191
• fix(falkordb): sanitize pipe and slash chars in fulltext queries by @Milofax in https://github.com/getzep/graphiti/pull/1183
• feat(nodes): generate entity summary from episode when no edges exist by @prasmussen15 in https://github.com/getzep/graphiti/pull/1196
• chore: bump version to 0.27.0pre2 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1200
• fix(falkordb): escape group_ids in RediSearch fulltext queries by @Milofax in https://github.com/getzep/graphiti/pull/1175
• feat(gemini): add support for Gemini 3 preview models by @geojaz in https://github.com/getzep/graphiti/pull/1202
• Fix Azure OpenAI integration for v1 API compatibility by @andreibogdan in https://github.com/getzep/graphiti/pull/1192
• fix(edges): preserve all signatures when edge type is reused across node pairs by @prasmussen15 in https://github.com/getzep/graphiti/pull/1197
• fix(graphiti): prevent add_triplet from overwriting edges with different src/dst by @prasmussen15 in https://github.com/getzep/graphiti/pull/1212
• bump version by @prasmussen15 in https://github.com/getzep/graphiti/pull/1219

New Contributors

• @Milofax made their first contribution in https://github.com/getzep/graphiti/pull/1183
• @geojaz made their first contribution in https://github.com/getzep/graphiti/pull/1202
• @andreibogdan made their first contribution in https://github.com/getzep/graphiti/pull/1192

Full Changelog: https://github.com/getzep/graphiti/compare/v0.26.3...v0.27.0

What's Changed

• Fix dependabot security vulnerabilities by @danielchalef in https://github.com/getzep/graphiti/pull/1184
• Revert "Fix dependabot security vulnerabilities" by @danielchalef in https://github.com/getzep/graphiti/pull/1185
• Pin mcp_server to graphiti-core 0.26.3 by @danielchalef in https://github.com/getzep/graphiti/pull/1186
• Update manual code review workflow to use claude-opus-4-5-20251101 by @danielchalef in https://github.com/getzep/graphiti/pull/1189
• Refactor prompt system for efficiency and clarity by @prasmussen15 in https://github.com/getzep/graphiti/pull/1191
• fix(falkordb): sanitize pipe and slash chars in fulltext queries by @Milofax in https://github.com/getzep/graphiti/pull/1183
• feat(nodes): generate entity summary from episode when no edges exist by @prasmussen15 in https://github.com/getzep/graphiti/pull/1196
• chore: bump version to 0.27.0pre2 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1200

New Contributors

• @Milofax made their first contribution in https://github.com/getzep/graphiti/pull/1183

Full Changelog: https://github.com/getzep/graphiti/compare/v0.27.0pre1...v0.27.0pre2

What's Changed

• Add extracted edge facts to entity summaries by @prasmussen15 in https://github.com/getzep/graphiti/pull/1182

Full Changelog: https://github.com/getzep/graphiti/compare/v0.26.3...v0.27.0pre1

What's Changed

• Add interface override paths for direct database calls by @prasmussen15 in https://github.com/getzep/graphiti/pull/1172

Full Changelog: https://github.com/getzep/graphiti/compare/v0.26.2...v0.26.3

What's Changed

• Remove filter_existing_duplicate_of_edges call from resolve_extracted_nodes by @prasmussen15 in https://github.com/getzep/graphiti/pull/1169

Full Changelog: https://github.com/getzep/graphiti/compare/v0.26.1...v0.26.2

What's Changed

• Move saga logic into retrieve_episodes utility function by @prasmussen15 in https://github.com/getzep/graphiti/pull/1167
• update by @prasmussen15 in https://github.com/getzep/graphiti/pull/1168

Full Changelog: https://github.com/getzep/graphiti/compare/v0.26.0...v0.26.1

What's Changed

• Add Sagas by @prasmussen15 in https://github.com/getzep/graphiti/pull/1149
• Add NotImplementedError fallback for GraphOperationsInterface methods by @prasmussen15 in https://github.com/getzep/graphiti/pull/1154

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.5...v0.26.0

What's Changed

• Edge extraction efficiency by @prasmussen15 in https://github.com/getzep/graphiti/pull/1140

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.4...v0.25.5

What's Changed

• use custom instructions in all extraction steps by @prasmussen15 in https://github.com/getzep/graphiti/pull/1148

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.3...v0.25.4

What's Changed

• Fix entity extraction for large episode inputs with adaptive chunking by @danielchalef in https://github.com/getzep/graphiti/pull/1129
• Bump version by @danielchalef in https://github.com/getzep/graphiti/pull/1139

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.2...v0.25.3

What's Changed

• chore: Add None defaults to DateFilter date field and PropertyFilter property_value field by @paul-paliychuk in https://github.com/getzep/graphiti/pull/1134
• bump version by @prasmussen15 in https://github.com/getzep/graphiti/pull/1138

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.1...v0.25.2

What's Changed

• Update Add Triple by @prasmussen15 in https://github.com/getzep/graphiti/pull/1133

Full Changelog: https://github.com/getzep/graphiti/compare/v0.25.0...v0.25.1

What's Changed

• Fix/model name config by @ronaldmego in https://github.com/getzep/graphiti/pull/1094
• Add SEO keyword to Zep link in README by @danielchalef in https://github.com/getzep/graphiti/pull/1114
• Add triplet update by @prasmussen15 in https://github.com/getzep/graphiti/pull/1115
• Custom prompt by @prasmussen15 in https://github.com/getzep/graphiti/pull/1122
• Fix limited number of edges by @prasmussen15 in https://github.com/getzep/graphiti/pull/1124

New Contributors

• @ronaldmego made their first contribution in https://github.com/getzep/graphiti/pull/1094

Full Changelog: https://github.com/getzep/graphiti/compare/v0.24.3...v0.25.0

What's Changed

• bump by @prasmussen15 in https://github.com/getzep/graphiti/pull/1093
• add property filters by @prasmussen15 in https://github.com/getzep/graphiti/pull/1099

Full Changelog: https://github.com/getzep/graphiti/compare/v0.24.2...v0.24.3

What's Changed

• [Doc]: fixing typos in various files by @didier-durand in https://github.com/getzep/graphiti/pull/1067
• Update default Anthropic model to claude-haiku-4-5 by @danielchalef in https://github.com/getzep/graphiti/pull/1070
• update summary character limit by @prasmussen15 in https://github.com/getzep/graphiti/pull/1073

Full Changelog: https://github.com/getzep/graphiti/compare/v0.24.0...v0.24.1

What's Changed

• Bump graphiti-core to v0.23.1 in mcp_server by @danielchalef in https://github.com/getzep/graphiti/pull/1060
• Use OpenAI structured output API for response validation by @danielchalef in https://github.com/getzep/graphiti/pull/1061
• Add Azure OpenAI example with Neo4j by @danielchalef in https://github.com/getzep/graphiti/pull/1064
• Add dynamic max_tokens configuration for Anthropic models by @supmo668 in https://github.com/getzep/graphiti/pull/1043
• [Doc]: fixing typos in various files by @didier-durand in https://github.com/getzep/graphiti/pull/1065
• Bump v0.24.0 by @danielchalef in https://github.com/getzep/graphiti/pull/1066

New Contributors

• @supmo668 made their first contribution in https://github.com/getzep/graphiti/pull/1043
• @didier-durand made their first contribution in https://github.com/getzep/graphiti/pull/1065

Full Changelog: https://github.com/getzep/graphiti/compare/v0.23.1...v0.24.0

What's Changed

• Fix entity edge save by @galshubeli in https://github.com/getzep/graphiti/pull/1013

Full Changelog: https://github.com/getzep/graphiti/compare/v0.23.0...v0.23.1

What's Changed

1. [Improvement] Add GraphID isolation support for FalkorDB multi-tenant architecture (#835)
2. Integrate MCP for FalkorDB (#910)
3. Implement build_indices_and_constraints for Kuzu and Neptune drivers (#1048)
4. update mmr to use bulk load overrides (#1029)
5. Fix Azure structured completions (#1039)
6. Enable FalkorDB fulltext search tests (#1050)
7. Fix: Enable FalkorDB Browser startup in MCP Server Docker image (#1045)
8. Add FalkorDB support for docker compose (#911)
9. Add MCP server release workflow (#1025)
10. Add automated FastAPI server container release workflow (#1031)
11. Fix MCP server release workflow to build all Dockerfile variants (#1037)
12. Potential fix for code scanning alert no. 24: Workflow does not contain permissions (#1036)
13. Disable fork PR comment job in workflow (#1047)
14. Search client update (#1026)
15. Bump version to 0.23.0 (#1056)
16. Add Zep vs Graphiti comparison table to README (#1014)
17. Update Zep comparison table description (#1046)

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0...v0.23.0

What's Changed

• Add Zep vs Graphiti comparison table to README by @jackaldenryan in https://github.com/getzep/graphiti/pull/1014
• Add FalkorDB support for docker compose by @Naseem77 in https://github.com/getzep/graphiti/pull/911
• Integrate MCP for FalkorDB by @Naseem77 in https://github.com/getzep/graphiti/pull/910
• Search client update by @prasmussen15 in https://github.com/getzep/graphiti/pull/1026
• Add MCP server release workflow by @danielchalef in https://github.com/getzep/graphiti/pull/1025
• update mmr to use bulk load overrides by @prasmussen15 in https://github.com/getzep/graphiti/pull/1029

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0...v0.22.1pre2

What's Changed

• Add Zep vs Graphiti comparison table to README by @jackaldenryan in https://github.com/getzep/graphiti/pull/1014
• Add FalkorDB support for docker compose by @Naseem77 in https://github.com/getzep/graphiti/pull/911
• Integrate MCP for FalkorDB by @Naseem77 in https://github.com/getzep/graphiti/pull/910
• Search client update by @prasmussen15 in https://github.com/getzep/graphiti/pull/1026

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0...v0.22.1pre1

What's Changed

• Refactor node extraction; remove summary from attribute extraction by @danielchalef in https://github.com/getzep/graphiti/pull/977
• Enforce shorter summaries with 8 sentence limit by @danielchalef in https://github.com/getzep/graphiti/pull/978
• Refactor summary prompts to use character limit and prevent meta-commentary by @danielchalef in https://github.com/getzep/graphiti/pull/979
• Refactor prompt structure: move MESSAGES after instructions by @danielchalef in https://github.com/getzep/graphiti/pull/980
• Add OpenTelemetry distributed tracing support by @danielchalef in https://github.com/getzep/graphiti/pull/982
• Bump pre-release version to 0.22.0pre4 by @danielchalef in https://github.com/getzep/graphiti/pull/983
• Remove JSON indentation from prompts to reduce token usage by @danielchalef in https://github.com/getzep/graphiti/pull/985
• bump 0.22.0pre5 by @danielchalef in https://github.com/getzep/graphiti/pull/986
• Add OpenTelemetry stdout example with Kuzu by @danielchalef in https://github.com/getzep/graphiti/pull/987
• Fix datetime comparison errors by normalizing to UTC by @danielchalef in https://github.com/getzep/graphiti/pull/988
• add search and graph operations interfaces by @prasmussen15 in https://github.com/getzep/graphiti/pull/984
• fix deprecated cypher pattern by @prasmussen15 in https://github.com/getzep/graphiti/pull/993
• Update README.md fix wrong link by @gkorland in https://github.com/getzep/graphiti/pull/768
• Separate unit, database, and API integration tests by @danielchalef in https://github.com/getzep/graphiti/pull/997
• Fix FalkorDB index deletion implementation by @danielchalef in https://github.com/getzep/graphiti/pull/998
• Secure Claude PR reviews with two-workflow approach by @danielchalef in https://github.com/getzep/graphiti/pull/999
• fix: wrap embeddings with vecf32() in FalkorDB single save paths by @Naseem77 in https://github.com/getzep/graphiti/pull/991
• Remove integration markers from database tests by @danielchalef in https://github.com/getzep/graphiti/pull/1000
• v0.22.0 bump by @danielchalef in https://github.com/getzep/graphiti/pull/1003

New Contributors

• @Naseem77 made their first contribution in https://github.com/getzep/graphiti/pull/991

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0...v0.22.0

What's Changed

• Remove JSON indentation from prompts to reduce token usage by @danielchalef in https://github.com/getzep/graphiti/pull/985
• bump 0.22.0pre5 by @danielchalef in https://github.com/getzep/graphiti/pull/986

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0pre4...v0.22.0pre5

What's Changed

• Add OpenTelemetry distributed tracing support by @danielchalef in https://github.com/getzep/graphiti/pull/982
• Bump pre-release version to 0.22.0pre4 by @danielchalef in https://github.com/getzep/graphiti/pull/983

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0pre3...v0.22.0pre4

What's Changed

• Refactor prompt structure: move MESSAGES after instructions by @danielchalef in https://github.com/getzep/graphiti/pull/980

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0pre2...v0.22.0pre3

What's Changed

• Refactor summary prompts to use character limit and prevent meta-commentary by @danielchalef in https://github.com/getzep/graphiti/pull/979

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0pre1...v0.22.0pre2

What's Changed

• Prompt for shorter summaries with 8 sentence limit by @danielchalef in https://github.com/getzep/graphiti/pull/978

Full Changelog: https://github.com/getzep/graphiti/compare/v0.22.0pre0...v0.22.0pre1

What's Changed

• Refactor node extraction; remove summary from attribute extraction by @danielchalef in https://github.com/getzep/graphiti/pull/977

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0...v0.22.0pre0

What's Changed

Since the release of v0.20.4 we have dramatically improved the quality of extractions, significantly reduced the number of runtime errors when adding an episode, and improved consistency and reliability of graph building.

• OpenSearch Integration for Neo4j by @prasmussen15 in https://github.com/getzep/graphiti/pull/896
• OpenSearch updates by @prasmussen15 in https://github.com/getzep/graphiti/pull/906
• Embedding fix by @prasmussen15 in https://github.com/getzep/graphiti/pull/917
• fix-fulltext-syntax-error by @galshubeli in https://github.com/getzep/graphiti/pull/914
• Graph quality updates by @prasmussen15 in https://github.com/getzep/graphiti/pull/922
• Skip entity attribute extraction when no fields defined by @danielchalef in https://github.com/getzep/graphiti/pull/924
• pre5 by @prasmussen15 in https://github.com/getzep/graphiti/pull/926
• don't save duplicate edges by @prasmussen15 in https://github.com/getzep/graphiti/pull/927
• Improve node deduplication w/ deterministic matching, LLM fallbacks by @danielchalef in https://github.com/getzep/graphiti/pull/929
• Bump v0.30.0pre0 by @danielchalef in https://github.com/getzep/graphiti/pull/932
• Refactor batch deduplication logic to enhance node resolution and track duplicate pairs (#929) by @danielchalef in https://github.com/getzep/graphiti/pull/936
• Update pyproject.toml to 0.30.0pre1 by @danielchalef in https://github.com/getzep/graphiti/pull/938
• Fix index out of range errors in LLM deduplication responses by @danielchalef in https://github.com/getzep/graphiti/pull/939
• chore: Bump version by @paul-paliychuk in https://github.com/getzep/graphiti/pull/940
• Improve node dedup prompts by @danielchalef in https://github.com/getzep/graphiti/pull/942
• bump 0.30.0pre3 by @danielchalef in https://github.com/getzep/graphiti/pull/946
• fix: Add edge type validation based on node labels by @danielchalef in https://github.com/getzep/graphiti/pull/948
• Allow Edge extraction to keep discovered edge labels by @danielchalef in https://github.com/getzep/graphiti/pull/950
• Improve JSON entity extraction prompt by @jackaldenryan in https://github.com/getzep/graphiti/pull/949
• Make natural language extraction configurable by @danielchalef in https://github.com/getzep/graphiti/pull/943
• 21 pre 7 by @prasmussen15 in https://github.com/getzep/graphiti/pull/954
• fix: Prevent duplicate edge facts within same episode by @danielchalef in https://github.com/getzep/graphiti/pull/955
• bump pre8 by @danielchalef in https://github.com/getzep/graphiti/pull/956
• chore: Update edge extraction prompt to paraphrase instead of quote by @danielchalef in https://github.com/getzep/graphiti/pull/957
• Bump version to 0.21.0pre9 by @danielchalef in https://github.com/getzep/graphiti/pull/958
• fix: Fix typo in JSON entity extraction prompt by @jackaldenryan in https://github.com/getzep/graphiti/pull/953
• Update Claude review prompt to focus on critical feedback by @danielchalef in https://github.com/getzep/graphiti/pull/960
• feat: Add optional callback to control node summary generation by @danielchalef in https://github.com/getzep/graphiti/pull/959
• Bump version to 0.21.0pre10 by @danielchalef in https://github.com/getzep/graphiti/pull/962
• Refactor issue workflows for improved automation by @danielchalef in https://github.com/getzep/graphiti/pull/964
• fix: Improve deduplication ID validation and logging by @danielchalef in https://github.com/getzep/graphiti/pull/965
• filter out falsey values before creating embeddings by @prasmussen15 in https://github.com/getzep/graphiti/pull/966
• Remove ensure_ascii configuration parameter by @danielchalef in https://github.com/getzep/graphiti/pull/969
• Optimize edge deduplication prompt for caching and clarity by @danielchalef in https://github.com/getzep/graphiti/pull/970
• fix: Improve edge extraction entity ID validation by @danielchalef in https://github.com/getzep/graphiti/pull/968
• Bump version to 0.21.0pre12 by @danielchalef in https://github.com/getzep/graphiti/pull/967
• validate nodes and edges aren't falsey by @prasmussen15 in https://github.com/getzep/graphiti/pull/973
• Add group_id parameter to language extraction function by @danielchalef in https://github.com/getzep/graphiti/pull/952
• Update issue triage workflow to allow non-write users for duplicate checks by @danielchalef in https://github.com/getzep/graphiti/pull/974
• remove generic aoss_client interactions for release build by @prasmussen15 in https://github.com/getzep/graphiti/pull/975

Full Changelog: https://github.com/getzep/graphiti/compare/v0.20.4...v0.21.0

What's Changed

• validate nodes and edges aren't falsey by @prasmussen15 in https://github.com/getzep/graphiti/pull/973

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre12...v0.21.0pre13

What's Changed

• Remove ensure_ascii configuration parameter by @danielchalef in https://github.com/getzep/graphiti/pull/969
• Optimize edge deduplication prompt for caching and clarity by @danielchalef in https://github.com/getzep/graphiti/pull/970
• fix: Improve edge extraction entity ID validation by @danielchalef in https://github.com/getzep/graphiti/pull/968
• Bump version to 0.21.0pre12 by @danielchalef in https://github.com/getzep/graphiti/pull/967

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre11...v0.21.0pre12

What's Changed

• Refactor issue workflows for improved automation by @danielchalef in https://github.com/getzep/graphiti/pull/964
• fix: Improve deduplication ID validation and logging by @danielchalef in https://github.com/getzep/graphiti/pull/965
• filter out falsey values before creating embeddings by @prasmussen15 in https://github.com/getzep/graphiti/pull/966

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre10...v0.21.0pre11

What's Changed

• fix: Fix typo in JSON entity extraction prompt by @jackaldenryan in https://github.com/getzep/graphiti/pull/953
• Update Claude review prompt to focus on critical feedback by @danielchalef in https://github.com/getzep/graphiti/pull/960
• feat: Add optional callback to control node summary generation by @danielchalef in https://github.com/getzep/graphiti/pull/959
• Bump version to 0.21.0pre10 by @danielchalef in https://github.com/getzep/graphiti/pull/962

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre9...v0.21.0pre10

What's Changed

• chore: Update edge extraction prompt to paraphrase instead of quote by @danielchalef in https://github.com/getzep/graphiti/pull/957
• Bump version to 0.21.0pre9 by @danielchalef in https://github.com/getzep/graphiti/pull/958

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre8...v0.21.0pre9

What's Changed

• fix: Prevent duplicate edge facts within same episode by @danielchalef in https://github.com/getzep/graphiti/pull/955
• bump pre8 by @danielchalef in https://github.com/getzep/graphiti/pull/956

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre7...v0.21.0pre8

What's Changed

• Improve JSON entity extraction prompt by @jackaldenryan in https://github.com/getzep/graphiti/pull/949
• Make natural language extraction configurable by @danielchalef in https://github.com/getzep/graphiti/pull/943
• 21 pre 7 by @prasmussen15 in https://github.com/getzep/graphiti/pull/954

Full Changelog: https://github.com/getzep/graphiti/compare/v0.30.0pre5...v0.21.0pre7

What's Changed

• don't save duplicate edges by @prasmussen15 in https://github.com/getzep/graphiti/pull/927

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre5...v0.21.0pre6

What's Changed

• Skip entity attribute extraction when no fields defined by @danielchalef in https://github.com/getzep/graphiti/pull/924
• pre5 by @prasmussen15 in https://github.com/getzep/graphiti/pull/926

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre4...v0.21.0pre5

What's Changed

• fix-fulltext-syntax-error by @galshubeli in https://github.com/getzep/graphiti/pull/914
• Graph quality updates by @prasmussen15 in https://github.com/getzep/graphiti/pull/922

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre3...v0.21.0pre4

What's Changed

• Embedding fix by @prasmussen15 in https://github.com/getzep/graphiti/pull/917

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre2...v0.21.0pre3

What's Changed

• OpenSearch updates by @prasmussen15 in https://github.com/getzep/graphiti/pull/906

Full Changelog: https://github.com/getzep/graphiti/compare/v0.21.0pre1...v0.21.0pre2

What's Changed

• OpenSearch Integration for Neo4j by @prasmussen15 in https://github.com/getzep/graphiti/pull/896

Full Changelog: https://github.com/getzep/graphiti/compare/v0.20.4...v0.21.0pre1

What's Changed

• Add return to add_triplet by @prasmussen15 in https://github.com/getzep/graphiti/pull/898

Full Changelog: https://github.com/getzep/graphiti/compare/v0.20.3...v0.20.4

What's Changed

• add episode bulk search results by @prasmussen15 in https://github.com/getzep/graphiti/pull/897

Full Changelog: https://github.com/getzep/graphiti/compare/v0.20.2...v0.20.3