Metis
Metis is a coding agent that boosts AI/LLM coding performance by 50% - Wholiver/metis
About Metis
A coding agent that searches, remembers, executes, and verifies across terminal and desktop.
Standalone application with built-in Metis CLI and Server runtime (no Node.js required):
Windows (x64) : Download Metis-*-win-x64-setup.exe or .zip from the latest GitHub Release .
Use /login for subscription providers or configure an API key. See Quickstart for the complete guide.
OpenCode DeepSeek V4 Flash Terminal-Bench 2.1 (89 tasks) 60 / 89 (67.42%) ⚠️ Single-thread flat tool execution
Plan & Build Dual Workflows — Safely investigate in read-only Plan mode, then execute approved plans with a live-updating checklist in Build mode.
Dual Interface for Terminal & Desktop — Work directly in your terminal via the rich interactive TUI, or use the dedicated React/Vite Desktop workspace on macOS and Windows.
Recursive Multi-Agent System — Native named agents ( coordinator , planner , implementer , reviewer , verifier ) with L0→L4 recursive delegation and Git Worktree isolation.
Durable Memory & Resumable Sessions — Project knowledge and decisions persist in SQLite across restarts, context compactions, and session forks.
Benchmark-Grade Reliability — Automated verification gates, video evidence inspection, and full Terminal-Bench & Harbor evaluation readiness.
Discussion
Sign in to join the discussion.
Loading comments…
Tagged
Alternatives to Metis
Tools in the same space, ranked by how they are performing in the directory.
CAIPE
Open-source multi-agent system for AI-powered platform engineering.
Open source/AI Agents- Open source/AI Agents
Monty Go
Pure-Go wrapper for Pydantic Monty Python interpreter via WASM + wazero - fugue-labs/monty-go
/AI AgentsXYZZY
Self-hosted multiplayer AI workspace: a team makes hard technical decisions with AI and keeps the receipts.
/AI AgentsCtx
Instant recall for coding agents.
Open source/Developer ToolsScanverity
Sourced resolution-risk evidence for prediction-market bots and research teams. Request a private-beta evaluation of 10 assessments over 30 days, with no paymen
/AI Agents