36 packages found
Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid
Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD saving
A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each s
MCP server for token-efficient large document analysis via the use of REPL state
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
MCP Docs Vector - Documentation vectorization and search via MCP
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and
Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce
Deterministic persistent memory for AI agents.
Persistent memory for AI agents. Agents forget. CI remembers.
Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicab
📜 An MCP server for conversation history search and retrieval in Claude Code
A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access
The unified web layer for AI agents. Search (8 engines), stealth browse, auth, and act on 24 platforms. One npm install,
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less to
A local Apple Documentation crawler and MCP server. Written in Swift.
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
memory-mcp-1file
Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches h
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
Hindsight: Agent Memory That Learns
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust bi
Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No A
🧠 Persistent memory for AI Agents. Free trial → https://portal.penfield.app/sign-up
Farnsworth SYNTEK — 7-layer recursive agent memory with context branching, holographic recall, and on-chain persistence.
MCP server for Russian EGRUL/EGRIP lookups via FNS open-data — open self-host (MIT) + hosted Pro tier (closed beta)
Tessera — Memory layer for every AI. 58 MCP tools, 54 REST endpoints, local-first, AES-256 encrypted.
Persistent memory system for AI coding assistants via MCP. Works with Claude Code, Cursor, Copilot, Windsurf, Cline.
Semantic code searcher and codebase utility
@DeusDataHigh-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in mil
(S)AGE - (Sovereign) Agent Governed Experience
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real bro