Claude Find
- 10 repo stars
- Updated June 10, 2026
- Cavinooo/claude-find
claude-find is an MCP server that pulls Deep Memory from across your Claude Code sessions when you need it.
About
claude-find is an MCP server that connects Claude Code to Deep Memory spanning your past coding sessions, so you can ask your agent to surface earlier reasoning, fixes, or file discussions instead of starting cold. developers who live in Claude Code accumulate weeks of context that normally stays locked in old sessions; this server exposes retrieval when you need it during build, ship, and operate loops. Install the claude-find npm package as a stdio MCP server in your Claude Code settings, then invoke memory tools when debugging regressions, reusing architecture choices, or continuing multi-day features. It is not a general knowledge base for non-Claude tools and does not replace git history or issue trackers—it specializes in Claude Code session memory. Expect intermediate setup comfort with MCP config; no hosted remote is declared in the registry metadata.
- Pull Deep Memory from across Claude Code sessions on demand via MCP
- npm stdio package claude-find (version 0.2.5)
- GitHub repository Cavinooo/claude-find for install and updates
- Designed for when you need prior session context without manually reopening projects
- stdio transport for local agent configuration
Claude Find by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add claude-find -- npx -y claude-findAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 10 |
|---|---|
| Package | claude-find |
| Transport | STDIO |
| Auth | None |
| Last updated | June 10, 2026 |
| Repository | Cavinooo/claude-find ↗ |
What it does
Search deep memory across past Claude Code sessions so your agent recalls decisions, snippets, and context you already explored.
Who is it for?
Best when you ship primarily in Claude Code and want MCP-accessible recall of prior session work.
Skip if: Skip if you're on Cursor-only or Codex-only stacks without Claude Code session history, or teams needing org-wide document search.
What you get
After you add claude-find, your agent can query cross-session Deep Memory so continuity returns without manual copy-paste archaeology.
- MCP tools that query cross-session Deep Memory
- Faster resumes on multi-day agent-assisted builds
By the numbers
- Server version 0.2.5
- npm identifier claude-find
- Transport: stdio only in registry metadata
README.md
claude-find
Pull deep memory from across your Claude Code sessions — when you need it.
Semantic search over all your past Claude Code sessions. Finds context by meaning and keywords. Searches the raw conversation transcripts, not compressed summaries, so Claude gets the full picture: reasoning, constraints, failed approaches, and decisions.
Setup
brew install bun ollama
bunx claude-find setup
setup starts Ollama, pulls the embedding model, sets session retention to permanent, and registers the MCP server with Claude Code. Sessions are indexed in the background on startup. Searches work immediately and return progressively more complete results as indexing continues.
Linux / Windows
Install Bun and Ollama, then run bunx claude-find setup. It detects your platform and guides you through anything missing.
Use it
In any Claude Code session:
/find that database migration we discussed last week
/find why we chose websockets over polling
/find the session where we kept getting timeout errors
/find refactoring the payment module across all projects
Claude searches your past sessions semantically, finds the relevant conversations, and synthesizes the context: what was tried, what failed, what constraints you set, and what decisions were made.
How it works
- Indexes all Claude Code session JSONL files from
~/.claude/projects/ - Extracts user + assistant messages, compact summaries, file paths from tool calls
- Enriches each chunk with metadata context (project, branch, files, date) for better retrieval
- Embeds conversation chunks using qwen3-embedding via Ollama (GPU accelerated)
- Searches with hybrid semantic + keyword (FTS5) merged via Reciprocal Rank Fusion
- Returns raw conversation chunks so Claude can synthesize with full context
After upgrading, run bunx claude-find index to rebuild the index with the latest improvements.
What makes this different
- Searches raw transcripts. Nothing lost through compression.
- Retroactive: works on all existing sessions immediately. No hooks needed.
- Permanent history: setup disables Claude Code's 30-day session cleanup so your sessions are searchable forever.
- Non-blocking: indexes in the background at startup. Searches work instantly, even mid-indexing.
- Uses compact summaries: Claude's own session understanding, boosted in ranking.
- Indexes tool call metadata: search by files touched, errors encountered.
- Fast: Ollama + GPU keeps indexing fast and memory bounded.
Requirements
License
MIT
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.
123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
Claude Code session-memory MCP, not a vector DB skill or generic note-taking plugin.
FAQ
Who is claude-find for?
claude-find is for developers using Claude Code who need to retrieve Deep Memory from previous sessions through MCP tools.
When should I use claude-find?
Use it whenever you resume work, debug something you fixed before, or need prior architectural notes that lived in an earlier Claude Code session.
How do I add claude-find to my agent?
Add the npm stdio MCP server claude-find (v0.2.5) in your Claude Code MCP configuration per the Cavinooo/claude-find repository instructions.