Recall
Installs Git post-commit and post-merge hooks to incrementally index changed files and update the shared memory after commits and merges.
Supports a bundled local Ollama embedder via an OpenAI-compatible API for semantic search while keeping data on the local network.
Uses OpenAI-compatible embedding endpoints, defaulting to OpenAI, to generate embeddings for semantic search with configurable model and vector size.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Recall
A self-hosted memory server that a team's AI coding agents share.
Coding agents start every session knowing nothing about your codebase. Recall gives them one memory they all share: conventions, decisions, requirements and known errors, stored on a server you run. Agents read and write it through MCP tools or plain HTTP. The Claude Code plugin briefs each new session from that memory and updates it every time someone commits.
Features
Session-start brief: A SessionStart hook loads the current repo's top facts and the team's global conventions into every new Claude Code session.
Incremental indexing on commit:
/recall:trackinstalls gitpost-commitandpost-mergehooks. Each commit runs a headless pass over the changed files and saves the facts it can back with at least twofile:linecitations.Deep codebase reads:
/recall:scoursplits a repo into slices, reads each one with a reader agent, checks the results with a skeptic agent, and asks you about anything ambiguous before it writes.Retrieval confidence and a relevance floor: Every fact stores a confidence score that lowers its rank. Search results carry a
relevancevalue, and matches belowRECALL_MIN_RELEVANCE(or a per-requestmin_relevance) are suppressed instead of returned as if they were good.Token-safe connect: You save the token once with a silent terminal prompt, and
/recall:connectreads it from~/.recall/token. The token never enters the chat.Shared, scoped memory: Projects keep facts apart, and a
globalproject holds team-wide conventions. Tokens carry a role (owner, admin, developer, viewer) and can be limited to one project.Hybrid search, local if you want it: Search combines full-text and vector similarity, then adjusts for age and use. It runs keyword-only with no embedder, or semantic with a bundled local Ollama model, so no data leaves your network.
Related MCP server: sugar
Quick start
You need Docker with Compose v2.
git clone https://github.com/gshepptech/recall && cd recall
./install.sh # writes .env with random secrets, starts Postgres and Recall
./install.sh embedder # optional: local Ollama embedder for semantic search
./install.sh add-user alice developer # mint a token for a teammateinstall.sh prints the owner token when the server is up at http://localhost:8000.
Each person then connects Claude Code. First, in a terminal, save the server URL and token. The token prompt does not echo:
read -rp 'Recall URL (http://host:8000): ' U; read -rsp 'Recall token: ' T; echo; \
mkdir -p ~/.recall; printf 'RECALL_URL=%s\nRECALL_TOKEN=%s\n' "$U" "$T" > ~/.recall/token; \
chmod 600 ~/.recall/token; unset TThen, inside Claude Code:
/plugin marketplace add gshepptech/recall
/plugin install recall@recall
/recall:connectRestart Claude Code. The recall_* tools and the session brief load from the next
session. Run /recall:scour . once to seed a repo and /recall:track to keep it
current. After that, ask in plain language: "remember that we return Result types at
service boundaries", or "what did we decide about the auth flow?"
The full walkthrough, including roles and troubleshooting, is in docs/setup.md.
How it works
flowchart LR
subgraph Clients
CC["Claude Code + Recall plugin"]
Hook["git hooks<br/>(/recall:track)"]
Other["Other agents, scripts, curl"]
end
subgraph Server["Recall server (FastAPI)"]
MCP["/mcp<br/>MCP tools"]
HTTP["/webhook/recall<br/>JSON commands"]
UI["/ web UI"]
Auth["Token auth<br/>role + project scope"]
Cmd["Command handlers"]
Rank["Ranking<br/>FTS + vector, recency,<br/>use, confidence"]
end
Store[("SQLite + sqlite-vec<br/>or PostgreSQL + pgvector")]
Embed["Embedder<br/>OpenAI-compatible API<br/>(Ollama or hosted)"]
CC --> MCP
CC -- session brief --> HTTP
Hook -- headless claude -p --> MCP
Other --> HTTP
MCP --> Auth
HTTP --> Auth
UI --> Auth
Auth --> Cmd --> Rank --> Store
Cmd --> EmbedThe server is one Python process. Agents call it over MCP (Streamable HTTP at /mcp)
or send JSON commands to /webhook/recall. Each request is checked against a token's
role and optional project scope before it reaches a handler. Saves embed the title
and content when an embedder is configured. Searches run full-text and vector queries,
merge them, then re-rank by age, access count and stored confidence. If the embedder
is missing or fails, search falls back to keyword-only and the response is marked
degraded.
SQLite is the default for a single machine. The Docker stack uses PostgreSQL with pgvector so several agents can write at once. See docs/architecture.md for the data model and request flow.
Configuration
Settings are read from .env (see .env.example). The main ones:
Variable | Default | Purpose |
| none | Owner token. Only this token can mint other tokens. |
|
| Bind address and port |
|
|
|
|
| SQLite file |
|
| PostgreSQL connection |
|
| Any OpenAI-compatible embeddings endpoint, such as Ollama at |
| none | Embedder key. Leave it empty for keyword-only search. |
|
| Embedding model name |
|
| Vector size. It must match the model, for example 768 for |
|
| Relevance floor from 0 to 1. |
|
| Half-life, in days, of the recency boost |
|
| How much access count lifts a result |
The HTTP commands and their fields are listed in docs/commands.md.
Development
python3 -m venv .venv && . .venv/bin/activate
pip install -e ".[postgres,dev]"
cp .env.example .env # set RECALL_TOKEN
python -m recall # SQLite server on :8000; first run asks two setup questions
pytest # unit and integration tests (each suite starts its own server)
ruff check .
python -m recall.tests.eval_retrieval # recall@k and relevance-floor sweep on a labelled corpusThe Claude Code plugin lives in plugin/: slash commands in commands/, the
reader and skeptic agents in agents/, and the hook scripts in scripts/.
License
MIT. Recall began from the open-source Zikra memory server; see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Shared, scoped, reviewable team memory for AI coding agents.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to share a local-first, versioned memory of decisions, conventions, tasks, conflicts, and handoffs over MCP and REST.3 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to store, search, and recall persistent project and cross-project memories locally over MCP, keeping architectural decisions, conventions, and error patterns available across sessions. Also optionally exposes a task server for autonomous task execution driven by that same memory store.-
- AlicenseNot gradedqualityAmaintenanceGives AI agents persistent, shared memory by ingesting notes, code, transcripts, and session captures, then serving token-optimized context and hybrid keyword/semantic search over MCP and REST. Agents can classify, promote, and synthesize stored material so each session builds on prior work instead of starting from zero.10 npmMIT
- FlicenseNot gradedqualityAmaintenanceA local-first MCP memory server that lets AI coding agents store, search, and recall project-specific and cross-project knowledge, so architecture decisions, preferences, error patterns, and coding guidelines persist across sessions. It also exposes optional task-queue tools for handing off autonomous work that draws on the same stored context.-