开源终端 AI 编程 Agent：以在线 Evidence Runtime 验证链（LLM 输出是 Claim、工具结果才是 Evidence）为核心，SWE-bench_Lite 官方评测 36.7% 实例级通过率（可复现报告）。支持 7 种推理范式、MCP 工具、多模型。Python。
Cross-referenced across 55 tracked directories
#2911
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
6/3/2026
Created
56
GitHub Stars
11
Forks
60
Open Issues
10/29/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
ucsandman
Full-featured agent toolkit for the DashClaw platform. 178+ methods across 30+ categories for governance and orchestration.
...moreoooscoos
Benzi is a coding AI agent + harness grounded in a live code map.
amol21p
MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection
...morekusdsuna
Sync AI agent rules across Claude, Cursor, Windsurf, Copilot and more. Write once, apply everywhere.