Memesh Llm Memory
MeMesh LLM Memory provides a lightweight, universal memory layer for AI, enabling persistent and searchable knowledge across sessions.
๐ English | ็น้ซไธญๆ | ็ฎไฝไธญๆ | ๆฅๆฌ่ช | ํ๊ตญ์ด | Portuguรชs | Franรงais | Deutsch | Tiแบฟng Viแปt | Espaรฑol | เธ เธฒเธฉเธฒเนเธเธข
<p align="center"> <h1 align="center">MeMesh LLM Memory</h1> <p align="center"> <strong>The lightest universal AI memory layer.</strong><br /> One SQLite file. Any LLM. Zero cloud. </p> <p align="center"> <a href="https://www.npmjs.com/package/@pcircle/memesh"><img src="https://img.shields.io/npm/v/@pcircle/memesh?style=flat-square&color=3b82f6&label=npm" alt="npm" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e?style=flat-square" alt="MIT" /></a> <a href="https://nodejs.org"><img src="https://img.shields.io/badge/node-%3E%3D20-22c55e?style=flat-square" alt="Node" /></a> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-compatible-a855f7?style=flat-square" alt="MCP" /></a> </p> </p>The Problem
Your AI forgets everything between sessions. Every decision, every bug fix, every lesson learned โ gone. You re-explain the same context, Claude re-discovers the same patterns, and your team's AI knowledge resets to zero.
MeMesh gives every AI persistent, searchable, evolving memory.
Get Started in 60 Seconds
Step 1: Install
npm install -g @pcircle/memesh
Step 2: Your AI remembers
memesh remember --name "auth-decision" --type "decision" --obs "Use OAuth 2.0 with PKCE"
Step 3: Your AI recalls
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.
Open the dashboard to explore your memory:
memesh
Who Is This For?
| If you are... | MeMesh helps you... |
|---|---|
| A developer using Claude Code | Remember decisions, patterns, and lessons across sessions automatically |
| A team building with LLMs | Share team knowledge via export/import, keep everyone's AI context aligned |
| An AI agent developer | Give your agents persistent memory via MCP, HTTP API, or Python SDK |
| A power user with multiple AI tools | One memory layer that works with Claude, GPT, LLaMA, Ollama, or any MCP client |
Works With Everything
<table> <tr> <td width="33%" align="center">Claude Code / Desktop
memesh-mcp
MCP protocol (auto-configured)
</td> <td width="33%" align="center">Any HTTP Client
curl localhost:3737/v1/recall \
-d '{"query":"auth"}'
memesh serve (REST API)
Any LLM (OpenAI format)
memesh export-schema \
--format openai
Paste tools into any API call
</td> </tr> </table>Why Not Just Use Mem0 / Zep?
| MeMesh | Mem0 | Zep | |
|---|---|---|---|
| Install time | 5 seconds | 30-60 minutes | 30+ minutes |
| Setup | npm i -g โ done | Neo4j + VectorDB + API keys | Neo4j + config |
| Storage | Single SQLite file | Neo4j + Qdrant | Neo4j |
| Works offline | Yes, always | No | No |
| Dashboard | Built-in (7 tabs + analytics) | None | None |
| Dependencies | 6 | 20+ | 10+ |
| Price | Free forever | Free tier / Paid | Free tier / Paid |
MeMesh trades: enterprise-scale multi-tenant features for instant setup, zero infrastructure, and 100% privacy.
What Happens Automatically
You don't need to manually remember everything. MeMesh has 4 hooks that capture knowledge without you doing anything:
| When | What MeMesh does |
|---|---|
| Every session start | Loads your most relevant memories + proactive warnings from past lessons |
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
Dashboard
7 tabs, 11 languages, zero external dependencies. Access at http://localhost:3737/dashboard when the server is running.
| Tab | What you see |
|---|---|
| Search | Full-text + vector similarity search across all memories |
| Browse | Paginated list of all entities with archive/restore |
| Analytics | Memory Health Score (0-100), 30-day timeline, value metrics, knowledge coverage, cleanup suggestions, your work patterns |
| 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, language selector |
Smart Features
๐ง Smart Search โ Search "login security" and find memories about "OAuth PKCE". MeMesh expands queries with related terms using your configured LLM.
๐ Scored Ranking โ Results ranked by relevance (35%) + how recently you used it (25%) + how often (20%) + confidence (15%) + whether the info is still current (5%).
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.
๐ฆ Team Sharing โ memesh export > team-knowledge.json โ share with your team โ memesh import team-knowledge.json
Real-World Usage
"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
Unlock Smart Mode (Optional)
MeMesh works fully offline out of the box. Add an LLM API key to unlock smarter search:
memesh config set llm.provider anthropic
memesh config set llm.api-key sk-ant-...
Or use the dashboard Settings tab (visual setup):
memesh # opens dashboard โ Settings tab
| Level 0 (default) | Level 1 (Smart Mode) | |
|---|---|---|
| Search | FTS5 keyword matching | + LLM query expansion (~97% recall) |
| Auto-capture | Rule-based patterns | + LLM extracts decisions & lessons |
| Compression | Not available | consolidate compresses verbose memories |
| Cost | Free, no API key | ~$0.0001 per search (Haiku) |
All 8 Memory Tools
| Tool | What it does |
|---|---|
remember | Store knowledge with observations, relations, and tags |
recall | Smart search with multi-factor scoring and LLM query expansion |
forget | Soft-archive (never deletes) or remove specific observations |
consolidate | LLM-powered compression of verbose memories |
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 |
Architecture
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.
Contributing
git clone https://github.com/PCIRCLE-AI/memesh-llm-memory
cd memesh-llm-memory && npm install && npm run build
npm test -- --run # 413 tests
Dashboard: cd dashboard && npm install && npm run dev
<p align="center"> <strong>MIT</strong> โ Made by <a href="https://pcircle.ai">PCIRCLE AI</a> </p>