NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Go modules
Go modules, #2364 by repository stars
Latest stable
v0.2.13
Last release 27 days ago
26 Oct 2026
Ships fairly regularly
a new release about every 2 weeks
Nearly every release is documented
notes for 32 of 32 stable releases
Nothing withdrawn
no release was ever pulled
9 months old
44 releases · first in 2026
Drag across the ruler to compare, or tap a release to open it.
v0.2.13 improves memory entity quality, Unicode display, and embedding diagnostics. Memory and the local Agency authority remain available in one mnem
v0.2.13 improves memory entity quality, Unicode display, and embedding diagnostics. Memory and the local Agency authority remain available in one mnemon executable.
NEVER, ONLY, and NOTE as entities. This reduces unrelated entity links while preserving technical names, domains, and file paths. Existing stored entities are not rewritten automatically.mnemon embed --status verify that the selected model can produce a nonempty embedding. The legacy ollama_available field continues to report provider reachability, while embedding_available reports model usability.See PR #169, PR #171, PR #173, and PR #168.
npm install --global @mnemon-dev/mnemon@0.2.13
mnemon --version
Existing npm-managed installations can also run mnemon update. Native archives are available for macOS, Linux, and Windows on amd64 and arm64, with SHA-256 checksums. Homebrew users can upgrade through the mnemon-dev/tap tap.
Windows ZCode users should refresh their installed user-level hooks after upgrading:
mnemon setup --target zcode --global --yes
Keep any existing MNEMON_DATA_DIR override when rerunning setup. mnemon embed --status now performs a small synthetic embedding request to verify the selected model; it sends no stored memories and follows the configured provider's normal billing and timeout behavior.
make test, including go vet ./..., on the release source.checksums.txt; the Homebrew cask version and all four supported archive checksums match this release.The release workflow completed successfully, including frontend checks, deterministic tests, six-platform builds, Homebrew publication, and npm publication.
Your coding agent can read these notes before it upgrades. Set up the MCP server →
One column per month.
Nothing published for this version
v0.2.12 fixes Pi memory guidance and Windows installation compatibility. Memory and the local Agency authority remain available in one mnemon executab
v0.2.12 fixes Pi memory guidance and Windows installation compatibility. Memory and the local Agency authority remain available in one mnemon executable.
mnemon remember and mnemon link calls instead of injecting Claude-only delegation instructions. Pi and Claude setup, reinstall, and scoped removal preserve each other's guides.HOME, and honor PI_CODING_AGENT_DIR for setup, detection, and removal..cmd shim. Preserve ordinary executable lookup and bound child-process runtime and output.See issue #164, PR #165, and PR #166.
npm install --global @mnemon-dev/mnemon@0.2.12
mnemon --version
Existing npm-managed installations can also run mnemon update. Native archives are available for macOS, Linux, and Windows on amd64 and arm64, with SHA-256 checksums. Homebrew users can upgrade through the mnemon-dev/tap tap.
Pi users must refresh the installed integration after upgrading, using the same scope as the original installation:
# Project-local installation: run from the project directory.
mnemon setup --target pi --yes
# User-global installation:
mnemon setup --target pi --global --yes
Then restart Pi or use /reload. Keep any existing PI_CODING_AGENT_DIR and MNEMON_DATA_DIR overrides when rerunning setup.
make test (including go vet ./...), 33 Pi callback/process regressions, and 13 npm distribution tooling tests on the merged release source.HOME unset, native and npm layouts, and original-asset controls.The release workflow completed successfully, including frontend checks, deterministic tests, six-platform builds, Homebrew publication, and npm publication.
v0.2.11 adds a local, read-only WebUI for exploring Mnemon memories and reduces false recall matches caused by common words accumulating as entities.
v0.2.11 adds a local, read-only WebUI for exploring Mnemon memories and reduces false recall matches caused by common words accumulating as entities. Memory and the local Agency authority remain available in one mnemon executable.
mnemon web to browse an overview, searchable and filterable memory library, Markdown reader, interactive relationship graph, entity explorer, and activity history. Store-scoped URLs preserve navigation and filters; views support manual refresh and visible-tab polling.See the workspace guide and PR #163.
max(20, 1% of active memories) memories from the known-entity expansion filter. This reduces automatic propagation of ordinary words and unrelated matches through entity overlap. Strict regex and dictionary extraction, and explicit entity handling, retain their existing behavior. Historical entities and relationship edges are preserved. See PR #160.npm install --global @mnemon-dev/mnemon@0.2.11
mnemon --version
mnemon web
Open http://127.0.0.1:8484. Keep the WebUI local; this release does not add remote/team authentication or memory editing.
Existing npm-managed installations can also run mnemon update. Native archives are available below for macOS, Linux, and Windows on amd64 and arm64, with SHA-256 checksums. Homebrew users can upgrade through the mnemon-dev/tap tap.
go build -o mnemon ., make test (including go vet ./...), and the Web server lifecycle integration test.Nothing published for this version
v0.2.10 improves Memory retrieval performance, storage efficiency, and OpenCode/Windows integrations. Memory and the local Agency authority remain ava
v0.2.10 improves Memory retrieval performance, storage efficiency, and OpenCode/Windows integrations. Memory and the local Agency authority remain available in one mnemon binary.
MNEMON_EMBED_KEEP_ALIVE.mnemon gc --compact for database compaction, including explicit handling of busy checkpoints.The committed benchmark compares the optimized Memory implementation with the preceding master revision, using five alternating runs at N=1/10/100/1,000/10,000. At N=10,000, median hybrid-recall CPU time improved from 93.06 ms to 66.53 ms and cumulative allocation fell by 37.7%; atomic batch-insert CPU time improved from 524.33 ms to 431.60 ms. These are synthetic local measurements, with small-input tradeoffs documented alongside the gains. Exact vector search remains exact.
See the full analysis and raw samples and 中文报告.
npm install --global @mnemon-dev/mnemon@0.2.10
mnemon --version
Existing npm-managed installations can also run mnemon update. Native archives are available below for macOS, Linux, and Windows on amd64 and arm64, with SHA-256 checksums. Homebrew users can upgrade through the mnemon-dev/tap tap.
To refresh existing OpenCode or ZCode integrations, rerun mnemon setup for that target with the original project/global scope, then restart the host application. Updating the binary alone does not replace previously installed hooks.
Generate Homebrew casks with postflight_steps to eliminate the deprecated postflight warning.
v0.2.9 improves memory corrections, multilingual recall, and installation reliability. Memory and the local Agency authority remain available in one mnemon binary.
supersedes links so a correction can demote an older insight during recall while preserving its history. Support the relation in import, related queries, and brief recall output.postflight_steps to eliminate the deprecated postflight warning.npm install --global @mnemon-dev/mnemon@0.2.9
mnemon --version
Existing npm-managed installations can also run mnemon update.
Native archives are available below for macOS, Linux, and Windows on amd64 and arm64, with SHA-256 checksums. Homebrew users can upgrade through the mnemon-dev/tap tap.
v0.2.8 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.8 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.7 fixes --readonly recall on Windows and when using a relative --data-dir path.
v0.2.7 fixes --readonly recall on Windows and when using a relative --data-dir path.
#, and %. This resolves the misleading SQL logic error: out of memory (1) failure in #123.The fix is included in PR #125, with native Windows and Linux CI coverage.
--readonly still assumes an immutable, static snapshot. It should not be used to follow a database that another process is actively changing.
Archives are available below for macOS, Linux, and Windows, each on amd64 and arm64. Verify the download against checksums.txt. Existing Homebrew Cask users can update with brew upgrade --cask mnemon.
aab97af8002bf0c8ac18d88da64293e41c9eb121.--readonly recall now resolves and encodes SQLite file URI paths correctly
on Windows and when --data-dir is relative to the current directory. This
fixes the misleading SQL logic error: out of memory (1) failure reported
in #123.mode=ro and immutable=1: they reject database
writes, preserve recall counters and oplog, and create no WAL/SHM sidecars.#, and %.v0.2.6 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.6 ships Mnemon Memory and the local Agency authority in one mnemon binary.
Nothing published for this version
v0.2.5 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.5 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.4 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.4 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.3 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.3 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.2 ships Mnemon Memory and the local Agency authority in one mnemon binary.
v0.2.2 ships Mnemon Memory and the local Agency authority in one mnemon binary.
Nothing published for this version
v0.2.1 — Memory Store Reliability
v0.2.1 strengthens Mnemon Memory's SQLite maintenance paths without changing the CLI or public command structure.
prune oplog entry for every soft-deleted insight, including the active count and configured capacity.edges table migration so schema detection works with foreign-key enforcement enabled.Existing stores already using the current four-edge schema are unchanged. For legacy stores whose constraint still permits the obsolete narrative edge type, the migration applies the existing four-graph policy: narrative edges are removed while all other edges are retained.
Release artifacts are available for macOS and Linux on amd64 and arm64.
brew install --cask mnemon-dev/tap/mnemon
# or
go install github.com/mnemon-dev/mnemon@v0.2.1Full changelog: v0.2.0...v0.2.1
v0.2.1 聚焦 Memory SQLite 存储可靠性:自动裁剪现在会逐条写入 oplog;旧版 edges 表迁移可在启用外键及存在孤立边的情况下安全完成,并避免探针残留或误删真实数据。本版本同时整理了 Memory / Agency 的内部包边界,不改变 CLI、协议或状态路径。
Nothing published for this version
v0.2.0 integrates Mnemon Agency Preview into the single mnemon executable while keeping Mnemon Memory as the established root command surface.
v0.2.0 integrates Mnemon Agency Preview into the single mnemon executable while keeping Mnemon Memory as the established root command surface.
View → Intent → Receipt interaction loop.mnemon agency ....mnemond is the local daemon and protocol role behind Agency. It is not a second executable, and it does not replace an Agent's planner, tools, provider, or model runtime.
Agency is opt-in and remains separate from Memory:
mnemon root, including remember, recall, and setup;mnemon setup continues to configure Memory;mnemon agency setup separately enables Agency for one project;.mnemon/agency directory.This release also fixes a Memory safety issue: conflict candidates are no longer silently removed, and cosine-only similarity is no longer sufficient to replace an existing memory.
Agency is actively evolving and is intended for evaluation and controlled use. Its command surface, Runtime integration, protocol, peer exchange, and on-disk/wire formats may change before an explicit stability milestone. This Preview status applies to Agency; Memory retains its separate product contract.
The obsolete experimental Harness surfaces and event-emission bridge, including mnemon event and MNEMON_HARNESS_EVENT_EMIT, have been retired without compatibility shims.
Release artifacts are available for macOS and Linux on amd64 and arm64. Windows archives are not published for v0.2.0.
brew install --cask mnemon-dev/tap/mnemon
# or
go install github.com/mnemon-dev/mnemon@v0.2.0Existing Homebrew Formula installations are migrated to the v0.2.0 Cask through the tap migration record.
Full changelog: v0.1.17...v0.2.0
v0.2.0 首次把 Mnemon Agency Preview 集成到单一 mnemon 可执行文件中。Memory 的根级命令、Store、SQLite 数据和既有 setup 链路保持独立;Agency 通过 mnemon agency ... 按项目单独启用,状态保存在 .mnemon/agency。
Agency 引入 View → Intent → Receipt 循环、Handling / Artifact / Reference 三类协作对象、Pi-first Hook 接入和显式 Peer 协作。Agency 仍处于持续迭代的 Preview 阶段,其命令、Runtime 接口、协议及持久化/传输格式可能继续变化;这不改变 Mnemon Memory 的独立产品契约和主使用链路。
v0.1.17 broadens setup support for additional coding hosts, fixes hook/runtime edge cases, and advances the experimental harness runtime work.
v0.1.17 broadens setup support for additional coding hosts, fixes hook/runtime edge cases, and advances the experimental harness runtime work.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon setup.mnemon remember / mnemon link directly instead of recursively spawning another subagent.go build -o mnemon ..Full changelog: https://github.com/mnemon-dev/mnemon/compare/v0.1.16...v0.1.17
Nothing published for this version
v0.1.16 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.16 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
v0.1.15 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.15 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon setup --target cursor now installs a Cursor integration, including a
Mnemon skill, prompt files, and Cursor lifecycle hooks under .cursor/ or
~/.cursor/. The session-start hook primes Cursor with Mnemon guidance and
memory status, the stop hook can nudge for durable-memory writeback, and an
optional pre-compaction hook can remind users to preserve durable context.mnemon setup --eject --target cursor removes the installed Cursor skill and
Mnemon hook entries while preserving unrelated Cursor hook configuration.cursor binary or ~/.cursor/ config directory is present.mnemon setup continue to keep formal integrations under cmd/ and
internal/.v0.1.14 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.14 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon setup for Claude Code from $HOME no longer writes relative hook commands into the user-global ~/.claude/settings.json. Mnemon now detects this collision, resolves symlinks, honors CLAUDE_CONFIG_DIR, and writes absolute hook paths so hooks work from any future session directory.go build -o mnemon .make test (147 E2E checks)go test ./... in a clean worktreemnemon_0.1.14_darwin_amd64.tar.gz, mnemon_0.1.14_darwin_arm64.tar.gzmnemon_0.1.14_linux_amd64.tar.gz, mnemon_0.1.14_linux_arm64.tar.gzmnemon_0.1.14_windows_amd64.zipchecksums.txtfloat32 values instead of
float64, cutting embedding storage size roughly in half while keeping the
public vector API and cosine-similarity calculations in float64.float64
embedding blobs to the new float32 storage format. The migration records its
completion in SQLite PRAGMA user_version and leaves malformed or
non-legacy-looking blobs untouched rather than blocking database startup.$HOME/.claude
collision. When mnemon setup is run from $HOME, the apparent local
.claude/ directory is actually Claude Code's user-global config directory;
Mnemon now writes absolute hook commands in that case so hooks resolve
correctly from every future Claude Code session directory.CLAUDE_CONFIG_DIR-aware coverage for Claude Code
config collision detection, plus regression tests that genuine project-local
installs keep relative hook paths.float32 vector
serialization, plus legacy float64 deserialization coverage for migration.GitHub Actions reported Node.js 20 deprecation warnings for upstream actions (actions/checkout, actions/setup-go, and goreleaser/goreleaser-action). T…
v0.1.13 expands Mnemon's host integration surface while keeping the stable release contract focused on the CLI, setup targets, storage behavior, and markdown/hook based agent integration. The larger harness work included in this tag remains experimental and is called out separately below.
This release adds mnemon setup --target hermes, a native shell-hook integration for Hermes Agent. The implementation uses Hermes' public hook surface rather than embedding Mnemon as a Hermes memory provider, so it follows Mnemon's existing model: hooks inject guidance and recalled context, while the LLM still decides what is worth storing.
The installer now:
hermes binary or an existing ~/.hermes/ config directory~/.hermes/skills/mnemon/SKILL.md~/.hermes/agent-hooks/mnemon/~/.hermes/config.yaml without removing unrelated Hermes settingsmnemon setup --eject --target hermes to remove only Mnemon-owned files and hook entriesThe hook mapping is:
on_session_start records Mnemon status and guide context for the next LLM callpre_llm_call injects recalled memory context using Hermes' {"context": "..."} shell-hook response shapepost_llm_call queues a lightweight remember/nudge reminder for the next turn instead of automatically writing memoryon_session_finalize queues compact/finalization guidance for later context preservationThis is one implementation path for the Hermes discussion in #2. It intentionally does not close that issue by itself; a Hermes MemoryProvider/plugin path can still be evaluated independently.
v0.1.13 also includes mnemon setup --target pi, which deploys Mnemon into Pi's native extension surface.
The Pi setup target writes:
skills/mnemon/SKILL.mdextensions/mnemon.tsThe extension maps Mnemon lifecycle behavior onto Pi events including resources_discover, session_start, before_agent_start, agent_end, and session_before_compact. This gives Pi sessions the same core Mnemon reminders and skill discovery pattern used by the other setup targets, while keeping storage operations in the standalone mnemon binary.
This tag includes a large experimental mnemon-harness beta surface. It is useful for internal and advanced evaluation workflows, but it is not part of the stable v0.1.13 public API contract.
Included harness work covers:
The harness remains default-off and should not be treated as a release-path dependency for mnemon setup or other stable CLI commands.
Homebrew users can upgrade with:
brew update
brew upgrade mnemon
Direct downloads are available below for:
The release workflow completed successfully and published GoReleaser artifacts plus the Homebrew formula. The release test job ran the E2E suite before publishing.
Additional local checks run before tagging:
go test ./internal/setup ./cmdgo build -o mnemon .bash scripts/check_bilingual_sync.shmake test (147 E2E checks passed)actions/checkout, actions/setup-go, and goreleaser/goreleaser-action). The release completed successfully; this is workflow maintenance to address later.archives.format, archives.format_overrides.format, and brews). The artifacts and Homebrew formula were still published successfully.Nothing published for this version
v0.1.12 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.12 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
v0.1.11 improves the documentation and installed agent guidance around the mnemon import workflow introduced in v0.1.10.
v0.1.11 improves the documentation and installed agent guidance around the mnemon import workflow introduced in v0.1.10.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
docs/IMPORT.md into the English canonical import guide.docs/zh/IMPORT.md as the Chinese import guide with the same schema reference, examples, command usage, output explanation, FAQ, and LLM extraction prompt.mnemon skill templates for Codex, Claude Code, Nanobot, and OpenClaw.mnemon import --dry-run <file> and mnemon import <file> to each skill's command list.memory_draft.json with schema_version: "1"content, category, importance, tags, entities, and optional created_atsource_index, target_index, edge_type, weight, and reasonmnemon import --dry-run before writingmnemon status, mnemon search, or mnemon recallerrors field because imports can partially succeedgo test ./...go build -o mnemon .git diff --checkmake build and make test.mnemon import on historical chat exports.v0.1.10 adds the first supported workflow for importing historical chat exports into Mnemon memory, plus a small Claude setup fix included since v0.1.
v0.1.10 adds the first supported workflow for importing historical chat exports into Mnemon memory, plus a small Claude setup fix included since v0.1.9.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon import <file> for bulk-importing memory draft JSON files into the active or selected store.mnemon import --dry-run to validate a draft without writing to SQLite.mnemon import --no-diff for trusted imports where every draft item should be inserted as new memory.schema_version: "1" memory draft schema under internal/importdraft.source, an insights array, and optional explicit edges.content, category, importance, tags, entities, per-insight source, and RFC 3339 created_at for preserving historical timestamps.source_index, target_index, edge_type, weight, and optional reason, allowing LLM-generated imports to preserve strong relationships that heuristics may not infer.docs/IMPORT.md with the full draft schema reference, field constraints, category guidance, importance guidance, edge-type guidance, examples, and operational notes.memory_draft.json.docs/USAGE.md with the new import command examples.created_at memories into a store that already contains newer memories.effective_importance before pruning. Import finalization inserts explicit edges, repairs temporal edges, refreshes touched insight scores, and only then runs AutoPrune.graph.EngineOptions and TemporalMode so import can skip real-time temporal edge generation without changing mnemon remember behavior.make build and make test; local release prep also passed go test ./..., go build -o mnemon ., and git diff --check.mnemon import <file> bulk-imports memory draft JSON files into a selected
Mnemon store. Imported insights use the normal write path for duplicate and
conflict detection, embeddings when Ollama is available, entity/causal/
semantic graph construction, lifecycle scoring, and capacity pruning.internal/importdraft defines the public draft schema for historical chat
imports:
schema_version, source, insights, and optional edgescontent, category, importance, tags,
entities, source, and RFC 3339 created_atsource_index, target_index, edge_type,
weight, and reasonmnemon import --dry-run validates draft structure without writing to the
database, and mnemon import --no-diff inserts all draft insights without
duplicate/conflict detection.memory_draft.json.created_at is older than existing store contents. The import path disables
real-time temporal edge generation, then repairs affected source timelines
after all backdated insights are written so imported memories are inserted
into the global chronological chain.AutoPrune runs. Import finalization inserts explicit edges, repairs
temporal edges, refreshes touched insight scores, and only then applies
pruning.EngineOptions with TemporalMode,
allowing import to skip real-time temporal generation without changing the
behavior of mnemon remember.v0.1.9 makes mnemon recall lighter for routine agent use.
v0.1.9 makes mnemon recall lighter for routine agent use.
mnemon recall now returns a compact JSON shape by default instead of the previous full debug payload.id, content, category, importance, intent, matched_via, confidence, and rounded score.signals, timestamps, access_count, tags, entities, source, traversal metadata, and the full embedded insight object are omitted from the default output.mnemon recall <query> --verbose to restore the previous full payload shape..results[].insight.id, .results[].signals, or .meta should either add --verbose or migrate to the new compact fields.--basic recall output is unchanged.feat(recall): make default output LLM-friendlydocs(release): prepare v0.1.9 notesrecall now emits a compact, LLM-friendly JSON shape by
default. The default result entries keep id, content, category,
importance, intent, matched_via, confidence, and rounded score,
while omitting verbose debug fields such as signals, timestamps,
access_count, tags, entities, source, and traversal metadata. (#3)recall payload remains available with --verbose for
scripts, debugging, and callers that still need meta, signals, or the
full embedded insight object.recall --verbose flag to restore the previous full recall response.v0.1.8 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.8 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
--embed-model global flag exposes the existing MNEMON_EMBED_MODEL env
var on the CLI, applied consistently across embed, recall, and
remember. Useful for switching to multilingual models such as
nomic-embed-text-v2-moe:latest on code-switched corpora without exporting
the env var. Note: switching to a model with a different output dimension
silently invalidates existing embeddings — backfill after changing.Nothing published for this version
v0.1.7 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.7 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon receipt, allowing users to show
memory activity with identifiers, timestamps, summaries, and relation metadata
without exposing stored memory content.v0.1.6 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.6 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
mnemon setup --target codex deploys the mnemon skill,
prompt files, and Codex lifecycle hooks (SessionStart, UserPromptSubmit,
Stop) into .codex/ or ~/.codex/. mnemon setup --eject --target codex
removes the installed Codex surface while preserving unrelated hooks.mnemon setup --target nanobot deploys a skill file to
.nanobot/skills/mnemon/SKILL.md (local) or ~/.nanobot/workspace/skills/mnemon/SKILL.md
(global, recommended). mnemon setup --eject removes it. Detection is automatic
when the nanobot binary or ~/.nanobot/workspace/ directory is present.cmd/
and internal/.Nothing published for this version
v0.1.5 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.5 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of this release's public stability guarantee.
Diff now sorts matches by Similarity descending before selecting the overall
suggestion. Previously, KeywordSearch ordered candidates by token overlap score,
so a high-keyword-score candidate classified as ADD could mask a lower-keyword-score
candidate with higher Jaccard similarity that should have been UPDATE or DUPLICATE."not" from negation words — it appears in virtually all
scientific prose and caused unrelated records to be classified as CONFLICT.ContentSimilarity) to
Jaccard (|A∩B|/|A∪B|) — penalises texts that share vocabulary but
differ in most tokens, preventing formulaic records from scoring as UPDATE.v0.1.4 focuses on stable CLI, storage, and entity-graph behavior.
v0.1.4 focuses on stable CLI, storage, and entity-graph behavior.
Note: harness modules, harness documentation, and harness evaluation assets in this repository remain experimental and are not part of the v0.1.4 public stability guarantee.
remember --entity-mode to choose merge, provided, or auto entity handling.e57a1223aa58a5ecbeedb1c7791a3b330cd55cb6 Add MNEMON_EMBED_DIMENSIONS for Matryoshka dimension truncation Support Matryoshka Representation Learning by
MNEMON_EMBED_DIMENSIONS env var for Matryoshka dimension truncation (e.g., 256-dim instead of 768)Nothing published for this version
Nothing published for this version
OpenClaw skill template: Added standard install metadata (Homebrew, go install) to SKILL.md frontmatter — OpenClaw can now auto-detect mnemon and offe
install metadata (Homebrew, go install) to SKILL.md frontmatter — OpenClaw can now auto-detect mnemon and offer installationmnemon setup --target openclaw --yes), plugin config reference, and uninstall instructions baked into the skillbrew install mnemon-dev/tap/mnemon # or: go install github.com/mnemon-dev/mnemon@latest
mnemon setup --target openclaw --yes
73aa3f101d17718c90994536eb8a9edabe0fcd8e Emphasize LLM-supervised positioning in README
agent:bootstrap) + plugin (before_prompt_build)mnemon setup --target openclaw now auto-deploys skill, hook, plugin, and configNothing published for this version
Persistent memory for LLM agents. Single binary, zero dependencies, works with Claude Code and OpenClaw.
Persistent memory for LLM agents. Single binary, zero dependencies, works with Claude Code and OpenClaw.
mnemon setup auto-detects Claude Code / OpenClaw and installs skill + hooksnomic-embed-text for vector similarity (works without it too)# Homebrew (macOS / Linux)
brew tap mnemon-dev/tap && brew install mnemon
# Go install
go install github.com/mnemon-dev/mnemon@v0.1.0
# Binary download
# See assets below for darwin/linux/windows builds
mnemon setup # detect Claude Code / OpenClaw, install skill + hooks
mnemon remember "user prefers dark mode" --cat preference --imp 3
mnemon recall "UI preferences" --limit 5
mnemon status
| Platform | Architecture | File |
|---|---|---|
| macOS | Apple Silicon (arm64) | mnemon_0.1.0_darwin_arm64.tar.gz |
| macOS | Intel (amd64) | mnemon_0.1.0_darwin_amd64.tar.gz |
| Linux | arm64 | mnemon_0.1.0_linux_arm64.tar.gz |
| Linux | amd64 | mnemon_0.1.0_linux_amd64.tar.gz |
| Windows | amd64 | mnemon_0.1.0_windows_amd64.zip |
Full changelog below.
Initial public release.
remember, recall, forget, search, status, logmnemon store list|create|set|remove)MNEMON_STORE environment variable and --store CLI flag for store selection~/.mnemon/mnemon.db to ~/.mnemon/data/default/nomic-embed-text)mnemon viz)mnemon setup interactive installer with --eject support