0xNyk/lacp
Control-plane-grade agent harness for Claude, Codex & Hermes: policy gates, verification/evidence loops, memory, and auditable execution.
Implements a 5-layer memory stack (session, Obsidian vault, ingestion pipeline, code intelligence, hash-chained provenance) with modular Python hooks for Claude Code execution, plus policy-driven routing across trusted local, sandboxed, and remote execution tiers (Daytona/E2B). Built around git worktree isolation and dmux/tmux session orchestration to enable safe multi-agent swarms while maintaining deterministic, auditable workflows with zero external CI dependencies.
Stars
84
Forks
12
Language
Shell
License
MIT
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/0xNyk/lacp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
bobmatnyc/claude-mpm
Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and...
affaan-m/everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and...
VoltAgent/awesome-claude-code-subagents
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
nyldn/claude-octopus
Multi-LLM orchestration plugin for Claude Code — 8 providers (Codex, Gemini, Claude, Perplexity,...
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code