A agentindex
Decision guide

Best tool for how you actually work

Pick the constraint that matters most. Each section lists matching tools computed live from the verified specs.

64 Privacy and self-hosting Open-source tools you can run on your own infrastructure, so code and traces never leave your network.
Coding agent
  • Aider — AI pair programming in your terminal, git-native.
  • Cline — Autonomous coding agent inside VS Code, with approval gates.
  • Continue — Open-source AI code assistant for VS Code and JetBrains.
  • Floci — A free, open-source local AWS emulator for dev, testing, and CI.
  • Goose — Block's open-source local AI agent.
  • Hermes Agent — The self-improving AI agent built by Nous Research.
  • Kilo Code — Open-source coding agent consolidating Cline and Roo.
  • Open Interpreter — Let an LLM run code on your machine.
  • OpenCode — A model-agnostic, local-first coding agent TUI.
  • OpenCode Autolearn — Self-improvement engine for OpenCode agents.
  • OpenHands — Open-source autonomous software engineer (formerly OpenDevin).
  • Pi — A minimal, extensible terminal coding-agent harness.
  • Roo Code — A community fork of Cline with extra modes.
  • Tabby — Self-hosted AI coding assistant for teams.
Agent framework
  • Agno — A high-performance multi-agent framework and runtime (formerly Phidata).
  • AutoGen — Microsoft's framework for multi-agent conversations.
  • AWS Strands Agents — AWS's model-driven, open-source agent SDK.
  • CrewAI — Role-playing multi-agent crews.
  • DSPy — Declarative, programmable prompt programming from Stanford.
  • Google Agent Development Kit — Google's code-first toolkit for production agents.
  • Haystack (deepset) — Production-grade RAG and agent pipelines from deepset.
  • LangChain — The broad framework for LLM applications and agents.
  • LangGraph — Graph-based agent orchestration from LangChain.
  • Letta — Stateful agents with long-term memory (formerly MemGPT).
  • LlamaIndex — The data framework for LLM applications.
  • Mastra — The TypeScript-first agent framework.
  • OpenAI Agents SDK — OpenAI's lightweight agents SDK (Swarm successor).
  • PocketFlow — A 100-line minimalist LLM framework, agentic-coding friendly.
  • Pydantic AI — Type-safe agent framework from the Pydantic team.
  • Semantic Kernel — Microsoft's SDK for enterprise AI orchestration.
  • Smolagents — Hugging Face's minimalist code-writing agents.
  • Vercel AI SDK — The TypeScript toolkit for building AI apps and agents.
Observability
  • Arize Phoenix — Open-source LLM tracing and eval.
  • Comet Opik — Open-source eval and tracing from Comet.
  • Helicone — Proxy-based LLM observability with instant cost tracking.
  • Laminar — Open-source observability and eval for AI agents.
  • Langfuse — The most-used open-source LLM observability tool.
  • Lunary — Open-source LLM observability and prompt management.
  • SigNoz — Open-source OpenTelemetry observability.
Evaluation
Instrumentation
  • OpenLLMetry — OpenTelemetry instrumentation for LLMs.
Guardrails
  • Guardrails AI — Validation and guardrails library for LLM applications.
  • LLM Guard — Open-source security toolkit for sanitizing LLM inputs and outputs.
  • NeMo Guardrails — NVIDIA's open-source toolkit for LLM guardrails.
Code intelligence
  • Claude Context (Zilliz) — Semantic code-search MCP over your entire codebase.
  • codebase-memory-mcp — Code-intelligence MCP server that indexes codebases into a knowledge graph.
  • CodeGraph — Pre-indexed, local code knowledge graph for agents.
  • Repomix — Pack a whole repository into one token-optimized file for AI context.
  • Serena — LSP-based semantic code tools for agents, as an MCP toolkit.
Inference engine
  • llama.cpp — C/C++ inference for GGUF models on any hardware.
  • LMDeploy — Efficient inference and serving for open models.
  • Ollama — Run large language models locally with one command.
  • SGLang — Fast serving and structured generation engine.
  • Text Generation Inference — Hugging Face's production LLM server.
  • vLLM — High-throughput self-hosted LLM serving engine.
Agent memory
  • Mem0 — Universal memory layer for AI agents.
  • Zep — Long-term memory service for AI assistants and agents.
LLM gateway
  • Executor — One MCP gateway to connect any agent to every tool.
  • LiteLLM — Open-source LLM gateway with cost tracking, routing, and fallbacks.
  • Portkey — AI gateway with caching, fallbacks, and observability.
Multiplexer
  • Herdr — A terminal agent multiplexer that runs all your coding agents in one place.
  • tmux — A terminal multiplexer for managing many terminal sessions at once.
See all 64 on the directory →
34 Bring your own key Provider-agnostic tools that work with any model, including local ones, so you are never locked to one vendor.
Coding agent
  • Aider — AI pair programming in your terminal, git-native.
  • Cline — Autonomous coding agent inside VS Code, with approval gates.
  • Continue — Open-source AI code assistant for VS Code and JetBrains.
  • Goose — Block's open-source local AI agent.
  • Hermes Agent — The self-improving AI agent built by Nous Research.
  • Kilo Code — Open-source coding agent consolidating Cline and Roo.
  • Open Interpreter — Let an LLM run code on your machine.
  • OpenCode — A model-agnostic, local-first coding agent TUI.
  • OpenHands — Open-source autonomous software engineer (formerly OpenDevin).
  • Pi — A minimal, extensible terminal coding-agent harness.
  • Roo Code — A community fork of Cline with extra modes.
  • Tabby — Self-hosted AI coding assistant for teams.
  • Void — An open-source Cursor alternative.
  • Zed (AI) — The high-performance editor with built-in AI.
Agent framework
  • Agno — A high-performance multi-agent framework and runtime (formerly Phidata).
  • AutoGen — Microsoft's framework for multi-agent conversations.
  • AWS Strands Agents — AWS's model-driven, open-source agent SDK.
  • Cloudflare Agents SDK — Stateful agents on Cloudflare Workers.
  • CrewAI — Role-playing multi-agent crews.
  • DSPy — Declarative, programmable prompt programming from Stanford.
  • Google Agent Development Kit — Google's code-first toolkit for production agents.
  • Haystack (deepset) — Production-grade RAG and agent pipelines from deepset.
  • LangChain — The broad framework for LLM applications and agents.
  • LangGraph — Graph-based agent orchestration from LangChain.
  • Letta — Stateful agents with long-term memory (formerly MemGPT).
  • LlamaIndex — The data framework for LLM applications.
  • Mastra — The TypeScript-first agent framework.
  • PocketFlow — A 100-line minimalist LLM framework, agentic-coding friendly.
  • Pydantic AI — Type-safe agent framework from the Pydantic team.
  • Semantic Kernel — Microsoft's SDK for enterprise AI orchestration.
  • Smolagents — Hugging Face's minimalist code-writing agents.
  • Vercel AI SDK — The TypeScript toolkit for building AI apps and agents.
Inference engine
  • llama.cpp — C/C++ inference for GGUF models on any hardware.
  • Ollama — Run large language models locally with one command.
See all 34 on the directory →
53 Free and open source Fully free, community-maintained tools. You pay only for the model tokens you choose to use.
Coding agent
  • Aider — AI pair programming in your terminal, git-native.
  • Cline — Autonomous coding agent inside VS Code, with approval gates.
  • Continue — Open-source AI code assistant for VS Code and JetBrains.
  • Floci — A free, open-source local AWS emulator for dev, testing, and CI.
  • Goose — Block's open-source local AI agent.
  • Hermes Agent — The self-improving AI agent built by Nous Research.
  • Kilo Code — Open-source coding agent consolidating Cline and Roo.
  • Open Interpreter — Let an LLM run code on your machine.
  • OpenCode — A model-agnostic, local-first coding agent TUI.
  • OpenCode Autolearn — Self-improvement engine for OpenCode agents.
  • OpenHands — Open-source autonomous software engineer (formerly OpenDevin).
  • Pi — A minimal, extensible terminal coding-agent harness.
  • Roo Code — A community fork of Cline with extra modes.
  • Tabby — Self-hosted AI coding assistant for teams.
  • Void — An open-source Cursor alternative.
Agent framework
  • Agno — A high-performance multi-agent framework and runtime (formerly Phidata).
  • AutoGen — Microsoft's framework for multi-agent conversations.
  • AWS Strands Agents — AWS's model-driven, open-source agent SDK.
  • DSPy — Declarative, programmable prompt programming from Stanford.
  • Google Agent Development Kit — Google's code-first toolkit for production agents.
  • Haystack (deepset) — Production-grade RAG and agent pipelines from deepset.
  • LangChain — The broad framework for LLM applications and agents.
  • LangGraph — Graph-based agent orchestration from LangChain.
  • LlamaIndex — The data framework for LLM applications.
  • Mastra — The TypeScript-first agent framework.
  • OpenAI Agents SDK — OpenAI's lightweight agents SDK (Swarm successor).
  • PocketFlow — A 100-line minimalist LLM framework, agentic-coding friendly.
  • Pydantic AI — Type-safe agent framework from the Pydantic team.
  • Semantic Kernel — Microsoft's SDK for enterprise AI orchestration.
  • Smolagents — Hugging Face's minimalist code-writing agents.
  • Vercel AI SDK — The TypeScript toolkit for building AI apps and agents.
Observability
Evaluation
Instrumentation
  • OpenLLMetry — OpenTelemetry instrumentation for LLMs.
Guardrails
  • Guardrails AI — Validation and guardrails library for LLM applications.
  • LLM Guard — Open-source security toolkit for sanitizing LLM inputs and outputs.
  • NeMo Guardrails — NVIDIA's open-source toolkit for LLM guardrails.
Code intelligence
  • Claude Context (Zilliz) — Semantic code-search MCP over your entire codebase.
  • codebase-memory-mcp — Code-intelligence MCP server that indexes codebases into a knowledge graph.
  • CodeGraph — Pre-indexed, local code knowledge graph for agents.
  • Repomix — Pack a whole repository into one token-optimized file for AI context.
  • Serena — LSP-based semantic code tools for agents, as an MCP toolkit.
Inference engine
  • llama.cpp — C/C++ inference for GGUF models on any hardware.
  • LMDeploy — Efficient inference and serving for open models.
  • Ollama — Run large language models locally with one command.
  • SGLang — Fast serving and structured generation engine.
  • Text Generation Inference — Hugging Face's production LLM server.
  • vLLM — High-throughput self-hosted LLM serving engine.
LLM gateway
  • Executor — One MCP gateway to connect any agent to every tool.
  • LiteLLM — Open-source LLM gateway with cost tracking, routing, and fallbacks.
Multiplexer
  • Herdr — A terminal agent multiplexer that runs all your coding agents in one place.
  • tmux — A terminal multiplexer for managing many terminal sessions at once.
See all 53 on the directory →
44 MCP-first Tools with first-class Model Context Protocol support, ready to connect to the growing MCP ecosystem.
Coding agent
  • Aider — AI pair programming in your terminal, git-native.
  • Augment Code — A context engine for large enterprise codebases.
  • Claude Code — Anthropic's agentic CLI coding assistant.
  • Cline — Autonomous coding agent inside VS Code, with approval gates.
  • Continue — Open-source AI code assistant for VS Code and JetBrains.
  • Cursor — The AI-first code editor built on VS Code.
  • Gemini CLI — Google's open-source terminal agent for Gemini.
  • GitHub Copilot — GitHub's AI pair programmer across editor and CLI.
  • Goose — Block's open-source local AI agent.
  • Hermes Agent — The self-improving AI agent built by Nous Research.
  • Kilo Code — Open-source coding agent consolidating Cline and Roo.
  • OpenAI Codex — OpenAI's open-source agentic coding CLI.
  • OpenCode — A model-agnostic, local-first coding agent TUI.
  • OpenHands — Open-source autonomous software engineer (formerly OpenDevin).
  • Pi — A minimal, extensible terminal coding-agent harness.
  • Roo Code — A community fork of Cline with extra modes.
  • Void — An open-source Cursor alternative.
  • Windsurf — Codeium's AI-native IDE (Cascade agent).
  • Zed (AI) — The high-performance editor with built-in AI.
Agent framework
  • Agno — A high-performance multi-agent framework and runtime (formerly Phidata).
  • AutoGen — Microsoft's framework for multi-agent conversations.
  • AWS Strands Agents — AWS's model-driven, open-source agent SDK.
  • Cloudflare Agents SDK — Stateful agents on Cloudflare Workers.
  • CrewAI — Role-playing multi-agent crews.
  • Google Agent Development Kit — Google's code-first toolkit for production agents.
  • Haystack (deepset) — Production-grade RAG and agent pipelines from deepset.
  • LangChain — The broad framework for LLM applications and agents.
  • LangGraph — Graph-based agent orchestration from LangChain.
  • Letta — Stateful agents with long-term memory (formerly MemGPT).
  • LlamaIndex — The data framework for LLM applications.
  • Mastra — The TypeScript-first agent framework.
  • OpenAI Agents SDK — OpenAI's lightweight agents SDK (Swarm successor).
  • Pydantic AI — Type-safe agent framework from the Pydantic team.
  • Semantic Kernel — Microsoft's SDK for enterprise AI orchestration.
  • Smolagents — Hugging Face's minimalist code-writing agents.
  • Vercel AI SDK — The TypeScript toolkit for building AI apps and agents.
Code intelligence
  • Claude Context (Zilliz) — Semantic code-search MCP over your entire codebase.
  • codebase-memory-mcp — Code-intelligence MCP server that indexes codebases into a knowledge graph.
  • CodeGraph — Pre-indexed, local code knowledge graph for agents.
  • Greptile — Hosted codebase intelligence for AI code review and Q&A.
  • Repomix — Pack a whole repository into one token-optimized file for AI context.
  • Serena — LSP-based semantic code tools for agents, as an MCP toolkit.
  • Sourcegraph — Enterprise code intelligence, search, and agent context.
LLM gateway
  • Executor — One MCP gateway to connect any agent to every tool.
See all 44 on the directory →
37 Hosted and managed Tools you sign up for, not infrastructure you run. No servers, no setup, just an API key or a login.
Coding agent
  • Augment Code — A context engine for large enterprise codebases.
  • Claude Code — Anthropic's agentic CLI coding assistant.
  • Cursor — The AI-first code editor built on VS Code.
  • Devin — Cognition's autonomous software engineer.
  • Gemini CLI — Google's open-source terminal agent for Gemini.
  • GitHub Copilot — GitHub's AI pair programmer across editor and CLI.
  • OpenAI Codex — OpenAI's open-source agentic coding CLI.
  • Replit Agent — Build and ship apps conversationally on Replit.
  • Void — An open-source Cursor alternative.
  • Windsurf — Codeium's AI-native IDE (Cascade agent).
  • Zed (AI) — The high-performance editor with built-in AI.
Agent framework
Observability
Evaluation
  • Braintrust — Evals and prompt playground for serious teams.
  • Galileo — Guardrails and evaluation for production LLMs.
  • Maxim AI — Evaluation and simulation for AI agents.
  • Patronus AI — Automated evaluation and guardrails for LLMs.
Code intelligence
  • Greptile — Hosted codebase intelligence for AI code review and Q&A.
  • Sourcegraph — Enterprise code intelligence, search, and agent context.
LLM provider
  • Anthropic — The Claude model API.
  • Cerebras Inference — Wafer-scale inference for very high throughput.
  • Cohere — Enterprise LLMs, embeddings, and rerankers.
  • DeepInfra — Low-cost hosted inference for open models.
  • Fireworks AI — Fast hosted open-model inference.
  • Google AI Studio — The Gemini API with a generous free tier.
  • Groq — Ultra-low-latency inference on custom LPU silicon.
  • Mistral AI — Provider of the Mistral and Codestral models.
  • Novita AI — Affordable hosted LLM and image APIs.
  • OpenAI — The GPT and Codex model API.
  • OpenRouter — One API routing to hundreds of models across providers.
  • Replicate — Run and host thousands of open models via API.
  • Together AI — Hosted open-model inference and fine-tuning.
  • Z.ai — Provider of the GLM family of models.
See all 37 on the directory →