Public catalog
67 tools. No owner fields. No holdings.
Imported from Crew's saved_tool export. Search name, tags, summary. Private notes, owner IDs, and AppSumo state never shipped.
67 matches · page 2 of 3
- repository google/mantis A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
- service GPT-Realtime-2 Model
- repository Graphify-Labs/graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
- repository HarnessRouter/harnessrouter HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
- repository headroom Headroom is an open-source context compression layer for LLM applications, available as a Python/TypeScript library, local proxy, agent wrapper, and MCP server. It compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach the model, with locally cached originals retrievable on demand.
- repository https://github.com/omnigent-ai/omnigent.git Omnigent is an open-source meta-harness and agent framework that provides a common orchestration layer over coding agents like Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and custom YAML-defined agents. It supports multi-agent sessions, policies, sandboxing, model switching, and real-time cross-device collaboration.
- service HubSpot Meeting Workflows — CRM-native meeting-completed email trigger Learn more about setting event enrollment triggers for your workflows.
- service Human-reviewed AI Evaluation Brief using approved Copilot or ChatGPT Learn best practices for designing evals to test and improve model performance in production.
- repository Hyper-Extract Hyper-Extract is a Python CLI for transforming unstructured documents into structured knowledge using LLMs. It supports graphs, hypergraphs, and spatio-temporal extractions via 80+ YAML templates, with providers including OpenAI, Anthropic, Gemini, DeepSeek, Bailian, and local vLLM.
- repository iamsrikanthnani/pluely The Open Source Alternative to Cluely - A lightning-fast, privacy-first AI assistant that works seamlessly during meetings, interviews, and conversations without anyone knowing. Built with Tauri for native performance, just 10MB. Completely undetectable in video calls, screen shares, and recordings.
- repository inkeep/open-knowledge Beautiful, AI-native markdown IDE and LLM wiki
- repository ix-infrastructure/Ix Understand any codebase instantly. System intelligence for codebases, built for humans and AI.
- service Judge We pride ourselves on a simple pricing model. Starting with unlimited reviews for free, with access to premium features for just $15pm. No hidden fees, no price hikes – just simple pricing.
- repository lemony-ai/cascadeflow Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
- service LiteLLM LiteLLM is the open-source AI gateway that puts your full AI stack behind one OpenAI-compatible key. Track and cap LLM spend, route to the right model, and self-host anywhere — even air-gapped. 140+ providers, 1,892 models.
- repository MaxMiksa/Autonomous-Company An autonomous company working 24/7 on your own PC - Windows/Linux/macOS.
- service MCP Directory - Model Context Protocol Technology Hub Discover Model Context Protocol (MCP) technology - Optimize your AI models context handling for better performance and reduced costs.
- service Microsoft Power Automate with AI Builder document processing Learn how to build and use document processing models in AI Builder.
- repository nidhinjs/prompt-master A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
- repository OmoiOS OmoiOS is an open-source, self-hostable platform that turns feature specs into pull requests using a supervised swarm of coding agents, with DAG-based task dependencies, isolated Daytona sandboxes, and support for multiple LLM backends.
- repository onyx Onyx is an open-source (MIT for the Community Edition) AI chat platform that connects to major LLM providers and adds RAG, agents, web search, code execution, and enterprise search via indexing connectors. It can be self-hosted in a lightweight Lite mode or a full Standard deployment.
- repository open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
- repository OpenKB OpenKB is an open-source CLI that compiles documents (PDF, Word, Markdown, URLs, and more) into a wiki-style knowledge base using LLMs, powered by PageIndex's vectorless, tree-based retrieval for long documents. It supports querying, chat, skill generation, and an optional bundled web UI.
- service OpenTools — Browse 2,500+ AI Tools, Models & MCP Servers Discover and compare over 2,500 AI tools, MCP servers, experts, and resources. The complete AI ecosystem for builders.