harnessclaw/harnessclaw-engine: An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control,…
Registered services and components
AI services, agent skills, MCP servers and open-source AI tools are recorded as separate kinds. Filter by kind, status and order, and open an entry to see its official source and last-checked date.
408 AI services currently indexed (discovery and verification are continuous)
Counted as one 'service' per product a user selects and contracts for (not per vendor). See /methodology for how we count and verify.
Verified: 0 / Partial: 408 / Unknown: 0 / Last successful registry snapshot: 2026-10-26 23:40:55
Indexed by kind: AI services 408 / Agent skills 61 / MCP servers 20932 / Open-source AI tools 4118
Global discovery: last run 2026-10-27 06:49 UTC / next run due now (next scheduled run)
Updating the directory…
4118 entries (showing 1471–1500)
HarnessRouter/harnessrouter: HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claud…
Description available in the original source language.
HarshaAtmon10/ATMON-10-MEGA-BRAIN: ATMON 10 MEGA BRAIN - Ultimate AI Assistant
harsii03/legal-ai-agent: Indian Legal First-Aid Agent
harumiWeb/exstruct: Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents v…
hasanov1/mchost-ai-bot: hasanov1/mchost-ai-bot
hasnain-a/cagliostro-v3-demo: Chat with the 146M cagliostro-v3 base model, with stats
hassaniqbal1/my-caption-app: My Caption App
Hatracc/qwen-image-2.1-uncensored-aio-loras: Uncensored Qwen 2.1 with All-In-One LoRAs
Description available in the original source language.
hbauzan/llm-semantic-visualizer: VHectorLab 3D - Semantic embeddings study tool in WebGL
HCF-STUDIOS/openhermit: OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, ma…
He-Tag/smallm-125m-inference: 125M German/English chat model, trained from scratch
he-yufeng/ContractGuard: AI agent that reads the fine print so you don't have to. Upload any contract → get red flags, unfair terms, and plain-English explanati…
he-yufeng/CoreCoder: Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly Nan…
he-yufeng/FindJobs-Agent: LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and …
headroomlabs-ai/headroom: Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens …
HeadyZhang/agent-audit: Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 …
Health-Yang/MineEcho: Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.
Description available in the original source language.
hecrj/icebreaker: A local AI chat app powered by 🦀 Rust, 🧊 iced, 🤗 Hugging Face, and 🦙 llama.cpp
Description available in the original source language.
hedgerow-dev/rowan: Static security scanner for AI applications: source code, model files, dependencies and agent/MCP config, with evidence for every finding.
heider-x/vela: AI-powered IDE for novel writing — local LLM + RAG, privacy-first, BYOK. For web fiction authors and creative writers.
heilashahidi/adversarial-openemr: Adversarial Platform — Clinical Co-Pilot
heizaheiza/Charles-mcp: Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts
HelgeSverre/ollama-gui: A Web Interface for chatting with your local LLMs via the ollama API
Helicone/helicone: 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
helixml/helix: ♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full p…