
Skills, hooks, memory and security layer for coding agent harnesses
- Freemium
- Open-source agent
- 305K GitHub stars
- AI models and LLM tooling

Skills, hooks, memory and security layer for coding agent harnesses

Visual platform for building and deploying agentic workflows and knowledge pipelines

Python library for building agents from a model, tools, prompt and middleware

Code knowledge graph that gives coding assistants shared, source-linked context

Open-source RAG engine with a document pipeline, hybrid search and visual agent workflows

Self-hosted AI gateway routing many providers through one local endpoint with fallback

Web crawler and hosted API that turns URLs into LLM-ready Markdown or JSON

Plugin that adds free frontier models to the dsh agent app without keys

Long-term memory layer for AI agents that stores typed facts and consolidates beliefs

Open-source framework for adding agent chat, generative UI and approvals to your app

Open-source knowledge framework for RAG Q&A, agent tasks and auto-built wikis

Gateway that trims context, remembers sessions and enforces rules for coding agents

Open-source Python framework for building production RAG pipelines and agents

Open-source SDK for building MCP apps and servers, with a hosted cloud for them

Open-source AI gateway in Go that routes LLM calls with budgets, fallbacks and MCP

Google's open-source Go toolkit for building and deploying AI agents

Open-source deep-research agent models, with a hosted MiroMind app

Python library that optimises prompts and code with reflective evolutionary search

Open-source Python framework for building and orchestrating multi-agent AI systems

Open-source gateway adding identity, policy and audit between AI agents and your systems

Ruby library with one API for 23 AI providers, tools and Rails conventions

One API that runs Codex, Claude Code and Hermes as the agent backend of your product
Local MCP server to set up, verify and check coverage of signed agent action records
Runs locallyOne MCP gateway for all your MCP servers, with code mode, permissions and audit
Not checked yetResearch papers, benchmarks, citations and topic experts for AI assistants

One compact entry point that finds, describes and runs hundreds of pay-per-call data tools
Checks a shop, payment link, paid API or token before an agent pays, plus injection scans
Runs locally
Calibration test showing whether an agent says it doesn't know at the right time

Route finder that helps agents pick an API or MCP server from about 40k measured services
Official PRIVAKU app facts, download links and site search for AI agents