by nfemmanuel
Persistent, shared memory for AI agents — facts, checkpoints, semantic search.
npm:iranti · local package141/wkpublished 5 mo ago
Storage, memory and knowledge management for agents.
Persistent, shared memory for AI agents — facts, checkpoints, semantic search.
Model Context Protocol (MCP 2026) Server with Tasks Extension for MemoryAI
Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents
CodeMesh from the terminal: a live graph of your codebase for Claude Code, Codex, Opencode and any MCP agent. No editor required.
On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.
The runtime layer for Agentic AI. Persistent memory, autonomous agents, and workflows that survive every session.
Durable, versioned memory for AI assistants. Remote memory needs a Pastepile subscription.
Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.
Connect any AI agent to your Synchronex workspace — portable memory, decisions, and workers.
PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.
Query Polymarket prediction markets via The Graph — 20 tools, 8 subgraphs
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。
A Model Context Protocol server that acts as an intelligent conversation state manager and development guide for LLMs, featuring comprehensive long-term memory with persistent project artifacts
Persistent memory for AI assistants. Store, search, and recall across sessions.
n8n community node: DeepSeek R1/Reasoner Chat Model with proper reasoning_content handling for tool calls. Fixes the 'Missing reasoning_content field' error when using AI Agent with tools. Connect this as the Chat Model sub-node to your AI Agent.
Vehicle specs, federal recalls, and OBD-II DTC reference for AI agents via MCP.
MCP server for .NET memory profiling — in-process heap snapshots via EventPipe with leak heuristics
Geocoding, walking/driving/cycling distances, route optimization, isochrones and POI search on OSM