🤖 All AI Agents

Open-source long-context super-agent for research, coding, and creation.

MiroThinker is a deep research agent optimized for complex research and forecasting tasks.

IntentKit is an open-source, self-hosted cloud agent cluster for managing collaborative AI agent teams.

LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.

Kortix is a company-grade AI command center that manages multiple AI agents through configuration and code.

Parlant is a framework for building reliable AI agents for customer interactions.

Cognee is a shared memory platform for AI agents, requiring just a few lines of code to use.

Headless browser for AI agents designed to bypass anti-bot detection.

TencentDB Agent Memory provides local long-term memory through a four-layer progressive pipeline, with no dependency on external APIs.

Ouroboros is an Agent OS for AI coding that transforms vague ideas into verifiable codebases through structured workflows.

Ollama is a tool for running and managing multiple AI models.

An automated AI research agent that enables training nano chat models on a single GPU.

vLLM is a high-performance, memory-efficient LLM inference and serving engine.

Beads is a tool that provides persistent, structured memory for coding agents.

HyperFrames is an open-source framework that converts HTML, CSS, and media into MP4 videos.

mcp-go is a Go implementation of the Model Context Protocol (MCP) for seamless integration of LLM applications with external data sources and tools.

Plano is an AI-native agent and data plane for agent applications, offering orchestration, security, observability, and intelligent LLM routing.

Build data-driven ChatGPTs using natural language.

A secure, vetted professional AI coding agent skill registry.

gptme is a personal AI agent that runs in the terminal, capable of writing code, using terminal commands, and browsing the web.

AdalFlow is a library for building and automatically optimizing language model applications.

Multi-LoRA inference server supporting efficient serving of thousands of fine-tuned models.

Neo.mjs is a self-evolving software organism that autonomously operates within applications through a multi-model cluster.

HAAS is a multi-layered autonomous agent swarm system based on OpenAI, designed to achieve fully autonomous task execution.