当你的 Agent 反复偏离目标、任务越做越复杂、刚踩过的坑下次还踩 —— sofagent 能约束其行为、拆解复杂任务、从错误中沉淀教训。
Copy the install, test the workflow, then decide if it earns a permanent slot.
The signal is softer here. Treat it like a pattern source unless it solves a very specific gap.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Not hard to test, not trivial to unwind. Worth trying if it closes a sharp gap.
GitHub health unknown. no security policy. 0 open issues make this testable, but not something to trust blind.
AI Agent
OpenClaw
Model
Multiple
Fastest way to find out if sofagent belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
# Visit: https://github.com/KongFangXun/sofagentRun this first. You will know quickly if the workflow earns a permanent slot.
# No automated removal — visit https://github.com/KongFangXun/sofagentNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ agents/ │ └─ sofagent/ ← installs here └─ settings.json
当你的 Agent 反复偏离目标、任务越做越复杂、刚踩过的坑下次还踩 —— sofagent 能约束其行为、拆解复杂任务、从错误中沉淀教训。