Local-first AI developer toolkit — knowledge base, code analysis, context management, and developer tools for LLM agents
Tool registry, two-phase action execution, and sandbox profiles for the Lodestar epistemic chain. Part of Lodestar, the trust layer for AI agents.
Pluggable cognitive layer — port of GCS v15.3 as an embeddable MCP cognitive kit. Provides reasoning, research, planning, creativity, reflection, security, knowledge, analysis, agency orchestration, and adaptive pipelines via MCP protocol.
Convert a PDF into GEP (Genome Evolution Protocol) retrieval bundles for EvoMap
Runtime state for AI coding agents. Instruments Node.js apps with zero code changes, captures error patterns with causal chains and arg shape diffs, outputs structured JSON that AI agents consume to fix bugs.
Workload-aware blast radius forecaster for PostgreSQL migrations
Blast-radius analysis and selective test execution for Rust workspaces
Git-aware code knowledge graph — incremental AST indexing on every commit, MCP server for AI assistants
Centrality analysis for dependency graphs and file-level import graphs
Universal relational schema intelligence for SQL databases (Postgres, MySQL, SQLite, ClickHouse). Understand your database before you touch it.
A secrets scanner with pattern matching, entropy analysis, and live validation
LIP — persistent, incremental code intelligence daemon. Blast-radius indexing, MCP server, LSP bridge, and semantic search in one binary.
PR review tool with blast radius awareness — opengrep + cartog + LLM
MCP server for Graphyn — exposes code intelligence tools to AI agents
Language-agnostic code intelligence graph engine — the heart of Graphyn
Architectural X-ray for your codebase. Live, local, agent-ready.
Agent-optimized git data MCP server — structured change manifests and full file snapshots for LLM agents