LakyFx/CogniLayer
Stop re-explaining your codebase to AI. Infinite speed memory + code graph for Claude Code & Codex CLI. 17 MCP tools, subagent protocol, hybrid search, TUI dashboard, crash recovery. Save 80-200K+ tokens/session.
# Technical Summary for CogniLayer Implements persistent knowledge graphs across AI agent sessions using tree-sitter AST parsing for code intelligence (caller/callee mapping, blast radius analysis) and hybrid FTS5 + vector search for semantic fact retrieval—replacing repeated file reads with targeted 500-token queries. Exposes 18 MCP tools for Claude Code and Codex CLI, plus a subagent memory protocol that routes research findings to persistent databases instead of flooding parent context, enabling multi-agent workflows where 40K-token dumps compress to 500-token summaries with on-demand retrieval.
Stars
16
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/LakyFx/CogniLayer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.