codebase-memory

LeanKG: Stop Burning Tokens. Start Coding Lean.

Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.

Self-maintaining and persistent codebase memory for AI coding agents — a deterministic AST index plus agent-written notes that flag themselves stale when the code changes. Works with Claude Code, Cursor, and Codex via MCP + CLI.

Multi-repository workflow isolation for Codex Desktop - one verified project-bound task per repo, codebase-memory indexes, and an optional controller with model-class routing, hash-chained ledger, and evidence-backed experience reuse

the memory layer of your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.

Local-first Markdown memory and knowledge graph for Pi: preserve decisions, recall across sessions, and explore notes with code.

Persistent codebase memory for AI coding agents. MCP server + CLI + dashboard.

DeepSeek Harness plugin that gives coding agents a real code graph: six MCP tools for symbol search, AST snippets, call-path tracing, architecture analysis, and an auto-started graph UI.

Evidence-backed execution harness for AI coding agents: plans, gates, artifacts, codebase memory, learning loop, and verified claims.

Tu código, convertido en memoria viva para cualquier IA: una araña 3D teje el grafo de conocimiento de tu repo y tu agente lo consulta por MCP.

Local AI agent memory layer for repeated developer tasks, fresh context packets, and low-token repo recall.

Universal multi-agent operating system for Google Antigravity, Gemini CLI, and Claude Code with 503+ pre-staged skills and 71 specialist agents across 23 canonical repositories.

AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance

Pi-agent wrapper around codebase-memory-mcp: derived code knowledge (call graphs, blast radius) over a harness-owned trust boundary

Design memory for AI coding.

Markdown wiki with full revision history, REST API and a built-in MCP server. Long-term codebase memory for coding agents — the companion layer to codebase-memory-mcp: the graph knows where code lives, go-wiki knows what it is for. Single Go binary.

Personal research lab: low-level systems experiments on macOS — a FASM x86-64 runtime and tools, a native GPT-2 runtime, and preregistered studies of KV-cache and hidden-state transfer between language models.

Persistent codebase memory for AI coding agents via inline @agent notes, repo-local skills, and lightweight Codex hooks.

Local code intelligence and project memory for Codex and Claude Code. Explore TypeScript, JavaScript and Prisma through call graphs, model usage and source context. Project-scoped MCP server with a shared CLI.