
Store and retrieve controlled AI news stimuli with provenance for misinformation research
Runs locally- Open source
- AI models and LLM tooling

Store and retrieve controlled AI news stimuli with provenance for misinformation research
Runs locally
Agent identity, scoped permissions and reusable proofs across MCP clients
Not checked yet
Rust build of Microsoft's markitdown that turns documents and web pages into Markdown
Runs locallyPaid human listeners judge your TTS audio in blind preference or human-vs-AI studies
Runs locallyAsk GPT, Claude, Gemini or Grok from inside the AI app you already use
Not checked yetShared mailbox, handoffs and file-clash warnings for your coding agents
Runs locally
Extract documents with per-field confidence, classify messages, detect 608 languages
Not checked yetLocal-first knowledge graph engine with GraphRAG search and a 46-tool MCP server
Runs locally
Pay-per-call keyword, review, creator and local-lead data inside ChatGPT or Claude
Not checked yetRead Opik traces, score them and save prompts from your coding assistant
Not checked yetConvert PDF, DOCX, XLSX and other files to Markdown with no key or account
Not checked yet
Delegate tasks from Claude.ai to your self-hosted OpenClaw agent with OAuth 2.1
Runs locally
Shutdown dates, replacements and change alerts for AI models from 8 providers
Not checked yetRun a seven-agent AI team from Claude Code, Codex, Cursor or ChatGPT
Not checked yetRead-only MCP tools that check AI replies against policies and export regression tests
Not checked yetCheck the key factual claims in AI output against live web sources
Not checked yetLLM API prices, workload cost estimates and the extra tokens non-English text uses
Runs locallySearch open AI model files with recorded SHA-256 hashes and license labels
Not checked yet
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyOne MCP tool that adds outside randomness so repeated prompts give varied answers
Not checked yetLet an agent find, launch and monitor rented GPUs with cost checks
Not checked yetMCP server for AI spend: signed receipts, token-waste audits and model cost comparison
Not checked yetLocal runtime for routing work between Claude Code, Codex, Cursor and other coding agents
Runs locallyFull Qdrant API as 58 MCP tools, with plain-text semantic, BM25 and hybrid search
Runs locally23 pay-per-call AI APIs for agents, paid in USDC on Base with the x402 protocol
Not checked yetRemote MCP server that transcribes and translates social video links and uploaded files
Not checked yetShared memory MCP that gives coding agents cited, editable pages built from your sources
Not checked yetOne persistent memory layer for ChatGPT, Claude, Cursor and other AI clients
Not checked yetSee what Ollama is really doing with your prompts, with plain-language fixes
Runs locallyConnect AI clients to your Dactic work context, built from your tools and team interviews
Not checked yetSee every kind of AI for ai models and llm tooling: tools, agents, MCP servers and skills.Ranked: the best AI for ai models and llm tooling.