Research & Data

Provide persistent memory for AI agents using the I-Lang protocol to enable data recall across different sessions and models.

Convert code into a queryable knowledge graph for humans and AI agents using live AST indexing for LSP and MCP.

Manage Google Ads accounts via MCP. Execute GAQL reads and secure two-phase mutations with full v24 API coverage for reliable ad campaign control.

Audit AI coding agents and project configurations for security flaws using static analysis, custom rules, and LLM-assisted verification.

Self-hostable, multi-LLM knowledge OS for individuals and teams. Gemini/Ollama, knowledge graph, real-time collaboration, AGPLv3 + commercial license.

Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

local-first background AI daemon for Logseq OG. Turns your notes into an agentic workspace with autonomous indexing, zero data leaks, and an optional MCP server. Inspired by Andrej Karpathy's LLM-Wiki.

Automate VRM avatar generation using an agent-driven, headless forge pipeline for consistent model creation.

Inspect and automate WPF applications through semantically aware tools via the Model Context Protocol.

MCP server for Strava — bring your activities, segments, athlete data, and training history into AI agents via Model Context Protocol.

AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 51 MCP tools. Persistent sessions, lessons learned, semantic search, Team Brain, managed Valkey/Redis. Free tier.

Meta-Agentic Ai Orchestration Platform For Developers and Data Scientists Developing Full-Cycle(E2E) AI Projects

Shared knowledge layer for human-agent teams. Agents search, classify, and manage knowledge alongside your team.

RAG MCP Registry Finder (RAGMap): subregistry API + MCP server + Firestore ingestion

Index codebases for AI agents with a single local binary providing semantic search, symbol graphs, and grep capabilities without API keys.

Automate coding tasks with a local-first AI runtime that features long-term memory and self-evolving capabilities.

Open-source private logbook with a local agentic layer. Long-living AI agents read what you record and propose what to do next. Hardware permitting, the models runs locally too. Matrix + Vodozemac for end-to-end encrypted sync between your own devices.

Secure AI agent tool calls by blocking destructive actions, redacting sensitive data, and enforcing human oversight with this universal security gateway.

ADAM — self-improvement layer for Claude Code. Observes session friction (corrections, retry loops, dead-ends, error loops, edit churn) via lightweight hooks and proposes targeted skills, memory entries, and agent edits. Auto-applies low-blast changes with cross-session evidence; queues everything else for review.

Provide Hermes agents with persistent semantic memory using SQLite truth storage and LanceDB vector retrieval for cross-session context management.

AI-powered skills for financial professionals. Comprehensive collection of finance, accounting, audit, and compliance skills for AI agents. IFRS/GAAP compliant with industry-specific applications.

Provide AI agents with modular skills to automate and manage Alibaba Cloud big data services using official APIs and SDKs.

Provide open-source tools to optimize content for AI-powered search engines and improve visibility with Generative Engine Optimization (GEO).

Provide Jina AI services as Unix commands for search, read, embed, rerank, and manage content with shell-style pipes and chaining.