Tribal

Registre officiel Données et bases de données

Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

OCI package ghcr.io/tribal-memory/tribal:0.4.1
Claude Code
claude mcp add tribal -e 'TRIBAL_DATABASE__URL=<TRIBAL_DATABASE__URL>' -e 'TRIBAL_PROJECT_REMOTE=<TRIBAL_PROJECT_REMOTE>' -e 'TRIBAL_PROJECT_NAME=<TRIBAL_PROJECT_NAME>' -e 'TRIBAL_SERVER__TRANSPORT=http' -e 'TRIBAL_SERVER__BIND_ADDRESS=0.0.0.0:8725' -e 'TRIBAL_PUBLIC_MCP_URL=http://127.0.0.1:8725/mcp' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -- docker run -i --rm ghcr.io/tribal-memory/tribal:0.4.1
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "tribal": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/tribal-memory/tribal:0.4.1"
            ],
            "env": {
                "TRIBAL_DATABASE__URL": "<TRIBAL_DATABASE__URL>",
                "TRIBAL_PROJECT_REMOTE": "<TRIBAL_PROJECT_REMOTE>",
                "TRIBAL_PROJECT_NAME": "<TRIBAL_PROJECT_NAME>",
                "TRIBAL_SERVER__TRANSPORT": "http",
                "TRIBAL_SERVER__BIND_ADDRESS": "0.0.0.0:8725",
                "TRIBAL_PUBLIC_MCP_URL": "http://127.0.0.1:8725/mcp",
                "OPENAI_API_KEY": "<your openai_api_key>",
                "ANTHROPIC_API_KEY": "<your anthropic_api_key>"
            }
        }
    }
}

Variables d'environnement

  • TRIBAL_DATABASE__URL obligatoire Postgres (pgvector) connection string. Tribal is self-hosted; you provide the database. The supported, complete deployment is docker-compose.yml.
  • TRIBAL_PROJECT_REMOTE obligatoire First-run only: the git remote that identifies the project bootstrapped on first start.
  • TRIBAL_PROJECT_NAME obligatoire First-run only: the name of the project bootstrapped on first start.
  • TRIBAL_SERVER__TRANSPORT Containerised transport: http or sse. The Docker image does not serve stdio; install the binary for stdio.
  • TRIBAL_SERVER__BIND_ADDRESS Address the server binds inside the container. Must be 0.0.0.0 (not the loopback default) for the published port to be reachable.
  • TRIBAL_PUBLIC_MCP_URL The URL clients use to reach the server (for example http://127.0.0.1:8725/mcp). Needed for OAuth dynamic client registration once the server binds a routable interface.
  • OPENAI_API_KEY secret Optional; only if an ingest or retrieval stage is configured to use OpenAI (defaults target a local Ollama).
  • ANTHROPIC_API_KEY secret Optional; only if a stage is configured to use Anthropic.

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Tribal
  2. Prerequisites
  3. Setup
  4. Running
  5. Development
  6. Licence

Tribal

A personal knowledge context engine for software development. Tribal captures learnings, debugging insights, heuristics, and decision rationale from development work, then makes that knowledge retrievable by coding agents via MCP (Model Context Protocol).

Prerequisites

  • Rust (stable toolchain, 1.89+)
  • Rust nightly (for rustfmt — rustup toolchain install nightly)
  • Docker (for local Postgres and test containers)
  • just — cargo install just
  • sqlx-cli — cargo install sqlx-cli --no-default-features --features postgres
  • cargo-deny — cargo install cargo-deny

Setup

git clone git@github.com:samfolo/tribal.git
cd tribal
just db-up
just db-migrate
just check
just test

Running

# Run the MCP server (stdio transport)
just serve

# Run with a specific project
just serve-project <project_id>

Development

# Format code (requires nightly rustfmt)
just fmt

# Lint and format check
just check

# Run all tests
just test

# Run unit tests only (no database required)
just test-unit

# Full pre-push check (format, lint, test)
just pre-push

# Regenerate sqlx offline query metadata
just sqlx-prepare

Licence

MIT

Questions fréquentes

Qu'est-ce que Tribal ?

Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.

Comment installer Tribal ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add tribal -e 'TRIBAL_DATABASE__URL=<TRIBAL_DATABASE__URL>' -e 'TRIBAL_PROJECT_REMOTE=<TRIBAL_PROJECT_REMOTE>' -e 'TRIBAL_PROJECT_NAME=<TRIBAL_PROJECT_NAME>' -e 'TRIBAL_SERVER__TRANSPORT=http' -e 'TRIBAL_SERVER__BIND_ADDRESS=0.0.0.0:8725' -e 'TRIBAL_PUBLIC_MCP_URL=http://127.0.0.1:8725/mcp' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -- docker run -i --rm ghcr.io/tribal-memory/tribal:0.4.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Tribal ?

Oui. Il attend TRIBAL_DATABASE__URL, TRIBAL_PROJECT_REMOTE, TRIBAL_PROJECT_NAME, OPENAI_API_KEY, ANTHROPIC_API_KEY, à renseigner dans sa configuration.

Tribal est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient Tribal ?

Il est publié par tribal-memory. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.