specivo/specivo repository overview

⁠Specivo

Your team's knowledge, finally findable.

Specivo is a self-hosted project tracker + team wiki + semantic search, with a built-in MCP server so AI agents can work inside the tracker instead of around it. Open source (AGPL-3.0), no per-seat pricing — you run it on your own server and own the data.

🌐 specivo.io⁠ · 📖 Docs⁠ · 💻 GitHub⁠

⁠What it does

• Track work — issues with types, statuses, priorities, assignees, subtasks, relations, versions, sprints, and recurring tasks.
• Keep knowledge — a per-project wiki with full Markdown, version history, and one-click revert.
• Find by meaning — hybrid search (full-text and semantic) finds work even when the words don't match: "login flow" and "auth sequence" resolve to the same thing.
• Work with AI agents — a built-in MCP server lets assistants read and update issues, wiki, and search — one config line, every action in an audit log.

⁠Quick start

The image needs PostgreSQL (with pgvector) and Redis. The compose file wires it all up:

git clone https://github.com/specivo/specivo.git
cd specivo
docker compose up -d

Create your first admin user:

docker compose exec api python -m specivo.cli.admin create \
  --login admin --email admin@localhost --password changeme

Open http://localhost:9933⁠ and sign in.

⁠Tags

• latest — the most recent stable release
• X.Y.Z (e.g. 0.2.0) — pinned versions

linux/amd64. The same image runs the web API and the Celery worker/beat (see the compose file).

⁠Configuration

Set via environment variables (see .env.example):

⁠Links

• Documentation: https://specivo.io/docs/specivo/⁠
• Source & issues: https://github.com/specivo/specivo⁠
• License: AGPL-3.0