Model-independent agent harness with persistent memory, MCP orchestration, skills, tools and local-first governance.
#agent-loop
7 posts
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — DeepSeek gets its own 7-tool agent loop in a sandboxed workspace, not just...
Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the wor...
A CLI-first autonomous coding agent where the actor never grades itself. Every edit is grounded in your repo's real topology and verified by...
Lightweight, general-purpose TypeScript agent runtime. Open-source alternative to Claude Agent SDK.
MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-...
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks...