The lightest universal AI memory layer. One SQLite file, any LLM, zero cloud. MCP + HTTP + CLI. Smart Recall, Knowledge Evolution, Auto-Capture, Interactive Dashboard.
Context compression plugin for Claude Code. Automatically trims large tool outputโJSON, CSV, YAML, stack traces, and logsโbefore it enters the context window. Works as a Claude Code plugin (automatic, zero-config) or as an MCP server (on-demand).
@pcircle-aiFAQ
memesh is a Claude Code plugin with 3 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes agentic-orchestration, memesh-review, memesh. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add PCIRCLE-AI/memesh-llm-memory> /plugin install memesh@pcircle-memesh
Repo: PCIRCLE-AI/memesh-llm-memory
๐ English | ็น้ซไธญๆ | ็ฎไฝไธญๆ | ๆฅๆฌ่ช | ํ๊ตญ์ด | Portuguรชs | Franรงais | Deutsch | Tiแบฟng Viแปt | Espaรฑol | เธ เธฒเธฉเธฒเนเธเธข
MeMesh โ the open-source memory layer for Claude Code & MCP agents. One SQLite file. No cloud. Plugs into any LLM.
MeMesh's retrieval is FTS5 alone โ no LLM, no embeddings on the hot path. Measured against the public LongMemEval-S benchmark (500 questions, MIT-licensed):
| System | R@5 | Source |
|---|---|---|
MeMesh (Mode A, via recallEnhanced()) | 95.60% | benchmarks/longmemeval/RESULTS.md |
| MemPalace | 96.6% | Vendor self-report |
| Supermemory | ~82% | Vendor estimate |
| Zep | 63.8% | LongMemEval paper |
| Mem0 | 49.0% | LongMemEval paper |
Re-runnable in ~10 seconds. Full instructions, dataset SHA256, raw per-question results, and known-failure analysis: benchmarks/longmemeval/REPRODUCE.md.
Your coding agent forgets between sessions. Every architecture decision, bug fix, failed test, and hard-won lesson has to be re-explained. Claude Code starts fresh, re-discovers old constraints, and burns context on things it should already know.
MeMesh gives coding agents persistent, searchable, evolving local memory. Install with npm, memory lives in ~/.memesh/knowledge-graph.db, plug into Claude Code or any MCP-compatible client.
[!IMPORTANT] Actively developed โ features may change between releases. Open an issue for bugs or feature requests.
MeMesh has two install paths that coexist. Most users want both. They write to the same memory database (~/.memesh/knowledge-graph.db), so memories captured in Claude Code chat appear in your shell, and vice versa.
flowchart TB
classDef client fill:#1f2937,stroke:#4b5563,color:#f9fafb,stroke-width:1px
classDef pathA fill:#1e3a8a,stroke:#3b82f6,color:#eff6ff,stroke-width:2px
classDef pathB fill:#14532d,stroke:#22c55e,color:#f0fdf4,stroke-width:2px
classDef db fill:#7c2d12,stroke:#f97316,color:#fff7ed,stroke-width:2px
subgraph clients["Where you use memesh from"]
direction LR
CC["Claude Code<br/>(chat + agent)"]:::client
TERM["Terminal / other<br/>MCP clients<br/>(Cursor, Cline...)"]:::client
end
subgraph paths["Two install paths"]
direction LR
A["<b>Path A โ /plugin install</b><br/>โโโโโโโโโโโโโโโ<br/>Lives in <code>~/.claude/plugins/</code><br/><br/>โข MCP tools in chat<br/>โข Auto-capture hooks<br/>โข <code>/memesh</code> skill<br/>โข Session-start banner"]:::pathA
B["<b>Path B โ npm install -g</b><br/>โโโโโโโโโโโโโโโ<br/>Lives in <code>$(npm prefix -g)/bin/</code><br/><br/>โข <code>memesh</code> shell command<br/>โข <code>memesh-mcp</code>, <code>-http</code>, <code>-view</code> bins<br/>โข For Cursor / Cline / other MCP"]:::pathB
end
DB[("Shared memory DB<br/><code>~/.memesh/knowledge-graph.db</code><br/>Same data, both paths see it")]:::db
CC -->|uses| A
TERM -->|uses| B
A --> DB
B --> DB
Which one do you need?
| What you want to do | Install path |
|---|---|
Use the /memesh skill inside a Claude Code conversation | Path A (plugin) |
| Get auto-capture (sessions โ lessons โ recall) in Claude Code | Path A (plugin) |
Run memesh remember / memesh recall / memesh doctor in any terminal | Path B (npm-global) |
Open the local dashboard via memesh serve (no npx lookup delay) | Path B (npm-global) |
Plug memesh-mcp into Cursor, Cline, or another MCP client | Path B (npm-global) |
| All of the above | Install both โ they don't conflict |
This is the most common confusion. Read this once and you'll save yourself the loop:
/plugin install memesh@pcircle-memesh from inside Claude Code โ installs Path A only. Gives you MCP tools, hooks, the /memesh skill. Does NOT put memesh on your shell PATH.memesh reindex / memesh update / memesh doctor typed in a normal terminal โ needs Path B (npm-global). Without it: zsh: command not found: memesh.# After /plugin install ..., also run this:
npm install -g @pcircle/memesh
If you only use memesh through Claude Code chat (never type memesh in a terminal), Path A alone is enough. Everyone else: install both.
If you use Claude Code, install MeMesh as a plugin from inside the CLI:
/plugin marketplace add PCIRCLE-AI/memesh-llm-memory
/plugin install memesh@pcircle-memesh
Claude Code wires hooks, skills, and the MCP server automatically. You get in-session auto-capture, proactive recall, the /memesh skill (remember / recall / learn / forget) inside the Claude Code conversation, and remember / recall / forget / learn available as MCP tools to the agent.
The MCP server runs directly from the plugin's bundled compiled output โ no npx lookup, no build step needed. If the native better-sqlite3 binding is missing on first start (e.g. after a Node major upgrade), the launcher self-heals by rebuilding it in-process.
This installs the plugin only. You can run CLI commands via
npx @pcircle/memesh <command>if you absolutely don't want a global install, but typing plainmemeshin a terminal will reportcommand not found. To get a real shellmemeshcommand, also run Option B below โ both paths coexist and share the same memory database. The "Install paths at a glance" diagram above covers this.
If you want the binary directly on your shell PATH (so plain memesh, memesh-mcp, etc. work in any terminal without the per-call npx lookup), or you want to expose memesh-mcp as a fixed-path stdio command to non-Claude-Code MCP clients (Cursor, Cline, terminal-only flows):
npm install -g @pcircle/memesh
First-install notes (one-time):
- Native modules โ
better-sqlite3andsqlite-vecinstall via prebuilt binaries on macOS (arm64/x64), Linux (x64/arm64), and Windows x64. On uncommon platforms or when prebuilds fail, you'll need a working C/C++ toolchain.- Embedding model โ the first call that triggers a local embedding (e.g.
recallwith semantic mode) downloadsXenova/all-MiniLM-L6-v2(~80 MB) into~/.memesh/models/. Subsequent calls are instant. The default retrieval path (FTS5) does not require this download.
If you installed via Option A (/plugin install memesh@pcircle-memesh), skip this step โ Claude Code wires plugin hooks automatically.
If you installed via Option B (npm install -g), the CLI is on your PATH and the MCP server is registered, but the Claude Code session hooks are not auto-wired. Without them you can still use memesh remember / recall manually, but the auto-capture loop (sessions โ lessons โ recall on next session) is silent.
memesh install-hooks # adds memesh's hooks to ~/.claude/settings.json
memesh doctor # verifies "Hooks wired into Claude Code" passes
The hooks coexist with any custom hooks you already have under ~/.claude/hooks/ โ install-hooks writes additive entries and never overwrites yours. To remove later: memesh uninstall-hooks.
The bash examples below assume
memeshis on yourPATH(Option B). Option A (plugin-only) users have two equivalent paths: ask in the Claude Code conversation (the/memeshskill + MCP tools cover the same flows), or replacememeshwithnpx @pcircle/memeshin any shell โ same flags, no global install needed.
memesh remember "Use OAuth 2.0 with PKCE for the new auth"
Or use the explicit form when you want a stable name and type for later filtering:
memesh remember --name "auth-decision" --type "decision" --obs "Use OAuth 2.0 with PKCE"
memesh recall "login security"
# โ Finds "OAuth 2.0 with PKCE" even though you searched different words
That's it. MeMesh is now remembering and recalling across sessions.
If you want to verify the install and local wiring end to end:
memesh doctor
Open the dashboard to explore your memory:
memesh serve
| If you are... | MeMesh helps you... |
|---|---|
| A developer using Claude Code | Auto-recall project decisions, file-specific lessons, and past failures as you work |
| A coding-agent power user | Share one local memory layer across MCP-compatible tools |
| A team experimenting with AI coding workflows | Export/import project knowledge without introducing hosted infrastructure |
| An agent developer | Add local memory through MCP, HTTP, or the CLI |
Claude Code / Desktop
memesh-mcp
MCP tools + Claude Code hooks
Any HTTP Client
curl localhost:3737/v1/recall \
-H "Content-Type: application/json" \
-d '{"query":"auth"}'
memesh serve (REST API)
Any LLM (OpenAI format)
memesh export-schema \
--format openai
Paste tools into any API call
| MeMesh | OpenMemory | Cursor Memories | Mem0 | Zep / Graphiti | |
|---|---|---|---|---|---|
| Best fit | Local memory for coding agents | Local/cross-client MCP memory | Cursor-native project memory | Managed app/agent memory | Temporal knowledge graphs |
| Install shape | npm install -g @pcircle/memesh | Local app/server flow | Built into Cursor | Cloud API / SDK / MCP | Service/framework setup |
| Storage | One local SQLite file | Local memory stack | Cursor-managed rules/memories | Hosted or self-hosted stack | Graph database |
| Cloud required | No | No for local mode | Depends on Cursor account/settings | Yes for platform | Usually yes/self-hosted |
| Claude Code hooks | First-class | MCP tools | No | MCP tools | Not Claude Code-specific |
| Dashboard | Built in | Built in | Cursor settings | Platform dashboard | Platform/graph tooling |
| Tradeoff | Simple local wedge, not enterprise scale | Broader local app footprint | Locked to Cursor | Strong managed platform, less local-first | Strong graph model, heavier setup |
MeMesh trades enterprise-scale managed infrastructure for instant local setup, inspectable storage, and coding-agent workflow hooks.
You don't need to manually remember everything. MeMesh has 7 hooks that capture and inject knowledge while you work:
| When | What MeMesh does |
|---|---|
| Every session start | Loads your most relevant memories + proactive warnings from past lessons |
| Before editing files | Recalls memories tied to the file or project before Claude writes code |
| Before bash commands | (Opt-in) Nudges Claude to dispatch high-verifiability commands (test, build, lint, migrate, deploy, benchmark) as background agents |
| When you ask to remember | Detects "remember this" / "guardar en memesh" / "sauvegarder dans memesh" / "่จไธไพ" intent (5 languages) and reminds Claude to use memesh |
After every git commit | Records what you changed, with diff stats |
| When Claude stops | Captures files edited, errors fixed, and auto-generates structured lessons from failures |
| Before context compaction | Saves knowledge before it's lost to context limits |
Opt out anytime:
export MEMESH_AUTO_CAPTURE=false
All configuration is via environment variables. Defaults are local-only and zero-network โ you don't need to set anything to get a working system.
| Variable | Default | What it does |
|---|---|---|
MEMESH_DB_PATH | ~/.memesh/knowledge-graph.db | Override the SQLite database location. |
MEMESH_AUTO_CAPTURE | true | Disable the auto-capture hooks (Stop, PreCompact) entirely. |
MEMESH_AUTO_DETECT_LLM | unset (auto-detect on) | Set to 0 to stop memesh using an API key it finds in your shell env. By default, if ANTHROPIC_API_KEY / OPENAI_API_KEY / OLLAMA_HOST is set and you have not configured a provider in ~/.memesh/config.json, memesh uses it for write-side LLM features (lesson extraction, auto-tagging, dream). Embeddings are unaffected โ they stay local ONNX (384-dim) unless you explicitly set embedder.provider. |
MEMESH_ENABLE_AGENTIC_ORCHESTRATION | unset | Set to 1 to enable an experimental working-model protocol (CTO / Orchestrator / Agents framing). Adds a session-start banner, a Bash command nudge, and verify_agent_work telemetry. The protocol's effectiveness is being instrumented, not yet proven โ opt in if you want to participate. Default is OFF: the core memory features work without this flag. |
MEMESH_AUTO_UPDATE | off | Auto-update policy. off (default) never auto-updates; patch allows X.Y.Z โ X.Y.Z+N; minor adds X.Y.Z โ X.Y+1.0; major allows any bump. When permitted, a detached npm install -g fires at session end (Stop hook) so it never blocks your work โ outcomes land in ~/.memesh/auto-update.log. Also settable as autoUpdate in ~/.memesh/config.json (env wins). When the installed version is deprecated by maintainers (security advisory), patch is force-allowed even on off โ minor / major bumps still stay manual to avoid silent behaviour drift. |
OPENAI_API_KEY | unset | Your OpenAI key. Used automatically for LLM features unless you set MEMESH_AUTO_DETECT_LLM=0 or configure a provider explicitly. |
OLLAMA_HOST |
memesh doctor prints the resolved configuration so you can see what's active.
When npm flags an installed version as deprecated (typically a security advisory), the next session-start prepends a strong โ ๏ธ MeMesh <ver> is DEPRECATED banner and memesh update-status surfaces the same line until you upgrade. The check is cached at ~/.memesh/update-check.<version>.json so a transient network failure can't dim the warning.
8 tabs, 11 languages, zero external dependencies. Access at http://localhost:3737/dashboard when the server is running.
| Tab | What you see |
|---|---|
| Insights | Memory insights โ weekly recaps and pattern proposals from the dreamer engine; one-click accept/reject |
| Search | Full-text + vector similarity search across all memories |
| Browse | Paginated list of all entities with archive/restore |
| Analytics | Memory Health Score, 30-day timeline, PM velocity + KG connectivity metrics, work patterns, cleanup suggestions |
| Graph | Interactive force-directed knowledge graph with type filters, search, ego mode, recency heatmap |
| Lessons | Structured lessons from past failures (error, root cause, fix, prevention) |
| Manage | Archive and restore entities |
| Settings | LLM provider config, instant language selector |
๐ง Smart Search โ Search "login security" and find memories about "OAuth PKCE". MeMesh uses FTS5 + sqlite-vec on the hot path, LLM-free, and the vector supplement still reaches across related wording.
๐ Search in scripts that don't use spaces โ Chinese, Japanese, Korean, Thai, Lao, Khmer and half-width katakana are indexed as overlapping character pairs, so a memory written as ใ่ณๆๅบซ้ท็งปๅไธๅฎ่ฆๅ ๅไปฝใ is found by searching ใๅไปฝใ โ not only by its exact full text. Text is normalised (NFC) on both the write and the query side, so memories typed on macOS or with a Korean or Vietnamese IME are found in either spelling.
๐ Scored Ranking โ Results ranked by relevance (30%) + recency (25%) + frequency (18%) + confidence (17%) + recall impact (10%).
๐ Knowledge Evolution โ Decisions change. forget archives old memories (never deletes). supersedes relations link old โ new. Your AI always sees the latest version.
โ ๏ธ Conflict Detection โ If you have two memories that contradict each other, MeMesh warns you.
๐ธ๏ธ Knowledge Graph Connectivity โ memesh kg backfill-relations --all-rules links orphan entities using tag co-occurrence, project clustering, session context, and name similarity โ no LLM required.
๐ฆ Team Sharing โ memesh export > team-knowledge.json โ share with your team โ memesh import team-knowledge.json
Imported bundles stay searchable, but MeMesh does not auto-inject imported memories into Claude hooks until you review or re-store them locally.
"MeMesh remembered that we chose PKCE over implicit flow three weeks ago. When I asked Claude about auth again, it already knew โ no re-explaining needed." โ Solo developer, building a SaaS
"We export our team's memory every Friday and import it Monday. Everyone's Claude starts the week knowing what the team learned last week." โ 3-person startup, shared knowledge base
"The dashboard showed me that 90% of my memories were auto-generated session logs. I started using
rememberdeliberately for architecture decisions. Game changer." โ Developer who discovered the Analytics tab
MeMesh works offline by default โ recall stays strictly LLM-free (95.60% R@5 on LongMemEval-S out of the box). Add an LLM API key only if you want LLM-augmented analysis flows on top: smarter session extraction, auto-tagging of new memories, lesson generation from failures, and dream compression:
memesh config set llm.provider anthropic
memesh config set llm.api-key sk-ant-...
Or use the dashboard Settings tab (visual setup):
memesh serve # opens dashboard โ Settings tab
Embeddings default to a local ONNX model (Xenova/all-MiniLM-L6-v2, 384-dim) โ no API key, nothing leaves your machine, and the default FTS5 recall path doesn't need them at all. To use a hosted or local-server embedder instead:
memesh config set embedder.provider openai # or: ollama
memesh config set embedder.model text-embedding-3-small
The embedder is configured independently of the chat LLM โ changing llm.provider never silently changes your embeddings. If you switch to an embedder with a different dimension (e.g. 384 โ 1536), MeMesh rebuilds the vector index automatically on the next write. Supported embedder.provider values: onnx (default, local), openai, ollama.
| Level 0 (default) | Level 1 (Smart Mode) | |
|---|---|---|
| Search | FTS5 + sqlite-vec, 95.60% R@5 | unchanged โ recall is LLM-free at every level |
| Auto-capture | Rule-based patterns | + LLM extracts decisions & lessons |
| Auto-tagging | Manual tags only | + LLM generates tags for new memories |
| Failure analysis | Not available | + LLM converts session errors into structured lessons |
| Compression | Not available | dream compress verbose memories |
| Cost | Free, no API key | ~$0.0001 per analysis call (Haiku) |
| Tool | What it does |
|---|---|
remember | Store knowledge with observations, relations, and tags |
recall | FTS5 + sqlite-vec search with multi-factor scoring (relevance, recency, frequency, confidence, recall impact) โ no LLM in the hot path |
forget | Soft-archive (never deletes) or remove specific observations |
export | Share memories as JSON between projects or team members |
import | Import memories with merge strategies (skip / overwrite / append) |
learn | Record structured lessons from mistakes (error, root cause, fix, prevention) |
user_patterns | Analyze your work patterns โ schedule, tools, strengths, learning areas |
verify_agent_work | Persist a verification report for background-agent work; reality-checks claimed file changes against git diff |
โโโโโโโโโโโโโโโโโโโ
โ Core Engine โ
โ (8 operations) โ
โโโโโโโโโโฌโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโ
โ โ โ
CLI (memesh) HTTP API (serve) MCP (memesh-mcp)
โ โ โ
โโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโ
โ
SQLite + FTS5 + sqlite-vec
(~/.memesh/knowledge-graph.db)
Core is framework-agnostic. Same logic runs from terminal, HTTP, or MCP.
Claude Code's plugin marketplace pins versions at install time and does not auto-update. To pick up a new release:
Option A โ /plugin UI: uninstall memesh@pcircle-memesh, then reinstall. Claude Code fetches the latest marketplace version.
Option B โ one-line script (no UI clicking, idempotent):
# If your plugin install is v4.2.5 or newer, the script ships inside it:
bash ~/.claude/plugins/cache/pcircle-memesh/memesh/<current-version>/scripts/upgrade-plugin.sh
# If you installed before v4.2.5 (i.e. you're on v4.2.4 or v4.2.3),
# the script isn't in your plugin yet. Use the npm-global copy instead:
bash "$(npm prefix -g)/lib/node_modules/@pcircle/memesh/scripts/upgrade-plugin.sh"
# (That assumes you've also run `npm install -g @pcircle/memesh`. If you
# haven't, this is also a good moment to โ see the "Install paths at a
# glance" section above for why most users want both paths.)
The script fast-forwards the marketplace cache, stages the new version under ~/.claude/plugins/cache/, installs runtime deps, and re-points installed_plugins.json. Restart Claude Code afterwards so the MCP server reconnects.
npm-global installs (npm install -g @pcircle/memesh) can self-update via memesh update. Source checkouts: git pull && npm install && npm run build.
Session start surfaces a one-line banner (throttled to once per 24h per version) when a newer release is available, and memesh doctor reports the upgrade target with the channel-specific command.
git clone https://github.com/PCIRCLE-AI/memesh-llm-memory
cd memesh-llm-memory && npm install && npm run build
npm test
npm run test:e2e-dashboard
Dashboard: cd dashboard && npm install && npm run dev
.claude-plugin/
marketplace.json
plugin.json
.gitattributes
.github/
CODEOWNERS
codeql/
codeql-config.yml
ISSUE_TEMPLATE/
bug_report.yml
config.yml
feature_request.yml
question.yml
security_vulnerability.yml
pull_request_template.md
workflows/
ci.yml
codeql.yml
deprecate-npm.yml
mutation-audit.yml
publish-npm.yml
.gitignore
.mcp.json
benchmarks/
longmemeval/
MANUAL-VERIFICATION.md
METHODOLOGY.md
REPRODUCE.md
results/
RESULTS.md
.gitkeep
mode-A-2026-05-03T12-31-26.json
mode-A-2026-07-28T21-36-54.json
mode-A-2026-07-29T08-15-09.json
mode-A-2026-07-31T04-52-22.json
mode-B-2026-05-03T12-55-57.json
mode-B-2026-07-28T21-54-01.json
mode-B-2026-07-29T08-14-48.json
mode-B-2026-07-31T05-09-44.json
mode-C-2026-05-03T12-56-25.json
README.md
run.mjs
CHANGELOG-4.0.1.md
CHANGELOG-4.0.2.md
CHANGELOG-4.0.3.md
CHANGELOG-4.0.4.md
CHANGELOG.md
CLAUDE.md
CODE_OF_CONDUCT.md
CODEMAP.md
CONTRIBUTING.md
dashboard/
dist/
index.html
index.html
package-lock.json
package.json
src/
App.tsx
components/
AnalyticsTab.tsx
AuthPrompt.tsx
BrowseTab.tsx
DoctorBanner.tsx
FeedbackWidget.tsx
GraphTab.tsx
Header.tsx
HealthScore.tsx
icons/
EntityIcon.tsx
InsightsBanner.tsx
InsightsTab.tsx
KnowledgeRadar.tsx
LessonsTab.tsx
LlmTelemetryPanel.tsx
MemoryAgeMatrix.tsx
MemoryLoopCard.tsx
MemoryRow.tsx
MemoryTimeline.tsx
OnboardingBanner.tsx
PatternCard.tsx
PmAnalyticsPanel.tsx
ProjectRoadmap.tsx
SearchTab.tsx
SettingsTab.tsx
TabNav.tsx
UserPatterns.tsx
lib/
api.ts
entity-display.ts
failure.ts
i18n.ts
signalMode.ts
main.tsx
styles/
global.css
tsconfig.json
vite.config.ts
DESIGN.md
dist/
cli/
assets/
d3.v7.min.js
view-live.d.ts
view-live.d.ts.map
view-live.js
view-live.js.map
view.d.ts
view.d.ts.map
view.js
view.js.map
core/
analytics.d.ts
analytics.d.ts.map
analytics.js
analytics.js.map
auto-tagger.d.ts
auto-tagger.d.ts.map
auto-tagger.js
auto-tagger.js.map
config.d.ts
config.d.ts.map
config.js
config.js.map
demo.d.ts
demo.d.ts.map
demo.js
demo.js.map
digest-validator.d.ts
digest-validator.d.ts.map
digest-validator.js
digest-validator.js.map
doctor.d.ts
doctor.d.ts.map
doctor.js
doctor.js.map
dreamer.d.ts
dreamer.d.ts.map
dreamer.js
dreamer.js.map
embedder.d.ts
embedder.d.ts.map
embedder.js
embedder.js.map
extractor.d.ts
extractor.d.ts.map
extractor.js
extractor.js.map
failure-analyzer.d.ts
failure-analyzer.d.ts.map
failure-analyzer.js
failure-analyzer.js.map
graph.d.ts
graph.d.ts.map
graph.js
graph.js.map
install-channel.d.ts
install-channel.d.ts.map
install-channel.js
install-channel.js.map
install-hooks.d.ts
install-hooks.d.ts.map
install-hooks.js
install-hooks.js.map
install-id.d.ts
install-id.d.ts.map
install-id.js
install-id.js.map
json-utils.d.ts
json-utils.d.ts.map
json-utils.js
json-utils.js.map
kg-backfill.d.ts
kg-backfill.d.ts.map
kg-backfill.js
kg-backfill.js.map
lesson-engine.d.ts
lesson-engine.d.ts.map
lesson-engine.js
lesson-engine.js.map
lifecycle.d.ts
lifecycle.d.ts.map
lifecycle.js
lifecycle.js.map
llm-client.d.ts
llm-client.d.ts.map
llm-client.js
llm-client.js.map
llm-telemetry.d.ts
llm-telemetry.d.ts.map
llm-telemetry.js
llm-telemetry.js.map
llm-validator.d.ts
llm-validator.d.ts.map
llm-validator.js
llm-validator.js.map
memory-tool.d.ts
memory-tool.d.ts.map
memory-tool.js
memory-tool.js.map
operations.d.ts
operations.d.ts.map
operations.js
operations.js.map
output-language.d.ts
output-language.d.ts.map
output-language.js
output-language.js.map
paths.d.ts
paths.d.ts.map
paths.js
paths.js.map
patterns.d.ts
patterns.d.ts.map
patterns.js
patterns.js.map
project-tags.d.ts
project-tags.d.ts.map
project-tags.js
project-tags.js.map
projects.d.ts
projects.d.ts.map
projects.js
projects.js.map
prompt-safety.d.ts
prompt-safety.d.ts.map
prompt-safety.js
prompt-safety.js.map
schema-export.d.ts
schema-export.d.ts.map
schema-export.js
schema-export.js.map
scoring.d.ts
scoring.d.ts.map
scoring.js
scoring.js.map
serializer.d.ts
serializer.d.ts.map
serializer.js
serializer.js.map
signal-scorer.d.ts
signal-scorer.d.ts.map
signal-scorer.js
signal-scorer.js.map
skill-usage-log.d.ts
skill-usage-log.d.ts.map
skill-usage-log.js
skill-usage-log.js.map
stats.d.ts
stats.d.ts.map
stats.js
stats.js.map
types.d.ts
types.d.ts.map
types.js
types.js.map
updater.d.ts
updater.d.ts.map
updater.js
updater.js.map
verifier.d.ts
verifier.d.ts.map
verifier.js
verifier.js.map
version-check.d.ts
version-check.d.ts.map
version-check.js
version-check.js.map
db.d.ts
db.d.ts.map
db.js
db.js.map
index.d.ts
index.d.ts.map
index.js
index.js.map
knowledge-graph.d.ts
knowledge-graph.d.ts.map
knowledge-graph.js
knowledge-graph.js.map
mcp/
launcher.d.ts
launcher.d.ts.map
launcher.js
launcher.js.map
server.d.ts
server.d.ts.map
server.js
server.js.map
tools.d.ts
tools.d.ts.map
tools.js
tools.js.map
skills-manifest.json
storage/
conflicts.d.ts
conflicts.d.ts.map
conflicts.js
conflicts.js.map
fts-index.d.ts
fts-index.d.ts.map
fts-index.js
fts-index.js.map
transports/
cli/
cli.d.ts
cli.d.ts.map
cli.js
cli.js.map
http/
retired-routes.d.ts
retired-routes.d.ts.map
retired-routes.js
retired-routes.js.map
server.d.ts
server.d.ts.map
server.js
server.js.map
mcp/
handlers.d.ts
handlers.d.ts.map
handlers.js
handlers.js.map
schemas.d.ts
schemas.d.ts.map
schemas.js
schemas.js.map
docs/
api/
API_REFERENCE.md
ARCHITECTURE.md
demo/
index.html
images/
dashboard-analytics.png
dashboard-browse.png
dashboard-graph.png
dashboard-search.png
memesh-logo.svg
platforms/
chatgpt.md
gemini.md
README.md
universal.md
eslint.config.js
hooks/
hooks.json
LICENSE
package-lock.json
package.json
README.de.md
README.es.md
README.fr.md
README.ja.md
README.ko.md
README.md
README.pt.md
README.th.md
README.vi.md
README.zh-CN.md
README.zh-TW.md
scripts/
audit/
baseline.json
mutation-sample.mjs
verification-audit.mjs
build-dashboard.mjs
check-consumer-audit.mjs
check-doc-claims.mjs
check-generated-mirror.mjs
check-schema-drift.mjs
check-tag-matches-version.mjs
check-version-coherence.mjs
copy-cli-assets.mjs
dashboard-e2e-smoke.mjs
generate-hook-core.mjs
generate-skills-manifest.mjs
hooks/
_generated/
core-paths.js
fts-index.js
_shared.js
post-commit.js
pre-bash-orchestration-nudge.js
pre-compact.js
pre-edit-recall.js
session-start.js
session-summary.js
user-prompt-intent.js
lib/
executable-targets.mjs
hook-files.mjs
npm-bin.mjs
published-version.mjs
postinstall-rebuild.mjs
release-verify.sh
run-tests-isolated.mjs
set-executable-bits.mjs
smoke-packed-artifact.mjs
smoke-test.mjs
... 200 moreยฉ 2026 Flowy ยท Free and open source
Built for Claude Code ยท Not affiliated with Anthropic
http://localhost:11434 |
| Override the Ollama endpoint when using a local Ollama provider. |