Discover AI Agents worth trusting
We discover candidate repos on GitHub by rule, analyze each one against its README and outside sources, and write bilingual, multi-dimensional profiles so you can judge an agent faster.
Codex Autoresearch
Run measurable optimization loops inside your codebase: give it a goal, a benchmark, and a boundary, and it experiments, keeps evidence, and leaves a reviewable patch.
Recently added
Weco Autoresearch
Iteratively optimize code, prompts, and ML workflows against metrics you define.
AgentBro
Monitor, respond to, and manage local coding agents from a floating desktop console.
Carbon Code
A DeepSeek-powered coding CLI that decomposes tasks, proposes code changes, and validates them with tests.
OpenCode Mobile
Run and review self-hosted OpenCode coding sessions from an Android phone.
Weaver Agent Platform
A self-hosted platform for deep research, tool use, browser automation, and sandboxed code execution.
AI Bank Statement Automation
Extract, redact, analyze, and query bank-statement PDFs with local or cloud models.