by Karry1123
Local architecture maps and caller impact analysis with directory clustering and utility folding.
npm:repograph-cli · local package335/wkpublished 10 d ago
Storage, memory and knowledge management for agents.
Local architecture maps and caller impact analysis with directory clustering and utility folding.
No-key travel MCP for Claude Desktop, Codex-style agents, Hermes, and other clients.
Local, branch-aware code search & relation graph. SQLite FTS5 + tree-sitter symbols + source-graph edges, exposed as an MCP server and CLI. No chat LLM required.
Autonomous development pipeline — aa: · ag: · audit: · AST graph · Harness · Specs · Impact analysis · Decision trail · Metrics · MCP server. Works with Cursor and Claude Code.
Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay
0.3.2. Free MIT; no account, key, or payment. Verifies record, not computation. Stable error codes.
TokST MCP Server: Streamable HTTP and stdio tools for persistent AI Agent memory, Sessions, and collaboration.
Persistent file-based memory for AI agents: inspectable, versionable, fully local.
YATS — Yet Another Token Saver. One-command MCP server that indexes your codebase into a knowledge graph so AI agents (Claude, Cursor, Copilot) can search and navigate it without burning tokens.
Advisory MCP tools: policy score, reasoning checklist, compression. To enforce, use delentia-guard.
MCP server for atrib's verifiable action layer. Lets agents query their own provable past from the local mirror.
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
Persistent memory for AI agents - save once, recall in every session, project and tool.
A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code
A live map of how a big codebase fits together, for Claude Code and for you, with a local import index, an MCP server and the Map.
The engine of your second brain: Markdown notes as database tables, for you and your agents.
MCP server that gives your coding agent the real call graph of your repo (where / who_calls / impact / trace / guard, cited file:line) plus compressed AST context.
The Gibson MCP server: one tool surface for every coding agent host. Every RPC of every SDK service, every SDK helper and every checked-in platform tool, over stdio or streamable HTTP on localhost.
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions