Your team's intent, parsed into action.
The open-source agent collaboration control plane for engineering teams.
Warning
Alpha — under active development, not production-ready. APIs, schemas, and configs may change without notice between commits.
Parsar is a team-first platform for dispatching, managing, and auditing AI coding agents. Send tasks from the tools your team already uses — chat, web UI, API — and get results back where they started: a thread, a PR, a webhook.
Agent execution goes through the independently deployed Agents API Core, whose qualified profiles include Claude Code, Codex, and MiniMax Code. Parsar keeps its own database for members, business assets, permissions and collaboration.
- Team-first. Shared queues, run history, and permissions — not single-player agent loops.
- Independent execution. Core owns models, runtime environments and execution; Parsar uses its public Agents API.
- Pluggable surfaces. Feishu / Lark ships today; Slack, Discord, and webhooks on the roadmap.
- Auditable. Every run is persisted: prompt, diff, logs, exit code.
- Self-hosted. Your code, your secrets, your machine. No telemetry.
Requires Docker with Docker Compose v2.
curl -fsSL https://raw.githubusercontent.com/MiniMax-AI-Dev/parsar/main/install.sh | bashOpen http://127.0.0.1:18080 and create the first owner account in the web setup flow. The first registered user is the administrator.
The installer writes generated config, secrets, database files, and runtime
state under ~/.parsar/.
For local development from a checkout:
make docker-build
./install.sh --image parsar:devThe default Compose stack starts PostgreSQL and the Parsar web control plane. Deploy Core separately and configure a distinct Core project credential for each workspace using the product integration guide. Asset management works independently; Agent execution requires this connection.
Architecture, tech stack, development setup, and coding conventions are all in CONTRIBUTING.md.
Found a vulnerability? Please file a private report via GitHub Security Advisories — see SECURITY.md for the full policy.
MIT — 100% open source, no "open core" split.