Permission-aware retrieval for AI systems: policy-enforced access to organizational knowledge.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Page-cited retrieval for embedded docs, datasheets, MISRA, CMSIS, and RTOS references.

Session-level (not fragment) local memory for AI coding agents: passively captures Claude Code, Codex, ZCode and Qoder conversations into one SQLite store, with provenance-cited retrieval and a human-only right to be forgotten.

Stores what AI agents learn — thoughts, decisions, session events and repo facts — in PostgreSQL with pgvector and serves it back through versioned MCP tools with hybrid vector-plus-full-text retrieval and budgeted context packs. Enables multiple agents to share one scoped, role-isolated long-term memory, with deliberate promotion of distilled candidates into durable memories.

Enables MCP hosts to spawn, supervise, and collect results from parallel panels of pinned-model OpenCode v2 agents for delegated tasks, reviews, and cross-model comparisons. Supports per-member roles, models, permissions, follow-up prompts, cancellation, and persisted result retrieval.

Bridges a local Figma development plugin to a local MCP server, letting the client read and write real canvas layers through the Figma Plugin API without consuming official MCP or Dev Mode quota. Supports layer and auto-layout editing, component and variable inspection, design-to-code context retrieval, and PNG/JPG/SVG/PDF export.

Provides AI assistants offline fuzzy search, precise section retrieval, and section listing over bundled mobile-development documentation, enabling natural-language lookups of components, hooks, guides, and best practices.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.

Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.

Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati

A self-hosted MCP memory server that gives every MCP-compatible agent a shared, persistent memory layer, so preferences, project conventions, and past decisions carry across sessions and across different agents and vendors. It combines hybrid keyword-plus-vector retrieval with automatic context injection, zero-config sync, and selective injection of memories by agent and priority.

Enables deterministic request screening and, after native owner approval, fixed-target DeadBolt enforcement actions such as kill, deny, revoke, and evidence retrieval through local stdio MCP. Model analysis can advise but cannot approve actions.

A local Python + SQLite MCP memory service that stores persona, shared experiences, facts, agreements, and unfinished work, then restores them within a context budget so a new model can continue the same conversation. It supports offline original-text persistence, Chinese keyword retrieval, provenance-tracked memories, persona versioning/rollback, and progressive fading of older events.

Enables Claude to search and read an organization's internal documents (Word, PDF, HTML, Markdown) through hybrid BM25 + vector retrieval, returning answers with exact citations while enforcing server-fixed role permissions, hiding confidential and superseded content, and logging the token cost of every request.

Read-only MCP tools for querying USDA FAS Global Agricultural Trade System census export and import records by partner country, year, month and HS10 code prefix, plus the release-date lists for each flow. Results are capped with notes on omitted rows, and responses carry release vintages and retrieval metadata.

Enables local creation and querying of projects, storage and retrieval of source text, reading and saving storyboard tables with revision-conflict protection, and Excel export through MCP tools backed by SQLite.