Awesome Agents

A fast and lightweight framework for creating decentralized agents with ease.

Let your AI agent get the sources behind logins and paywalls.

AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

CLI is all you need. The agent CLI harness.

Simulate anything, for $1 & less than 10 min - Universal Swarm Intelligence Engine

Simulate anything, for $1 & less than 10 min - Universal Swarm Intelligence Engine

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Build agents which are controlled by LLMs

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

Autonomous GPT-4 agent platform

A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

data-to-paper: Backward-traceable AI-driven scientific research

Self-improving Agents

SkyAGI: Emerging human-behavior simulation capability in LLM

Make your meetings accessible to AI Agents

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.

RAG evaluation without the need for "golden answers"

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

The easiest, and fastest way to run AI-generated Python code safely

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

🧠 Second Brain AI agent

(S)AGE - (Sovereign) Agent Governed Experience

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

AI agent builder with a VM at its heart. Every agent gets its own microVM sandbox to install software, run code and use the GPU in. Python, Node.js and Rust.

Self-Programming AI Agent Framework. Agents create and refine their own workflows.

Kapso by Leeroo: A self-improving AI software factory (for measurable objectives). #1 open-source on MLE-Bench; ALE-Bench; RelBench

Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.

Lossless storage and search for AI agent sessions, across every agentic client.

Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.

AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports. Supports AWS Bedrock and Anthropic API. Features automated analysis of logic, security, performance, and code quality with smart token efficiency through prompt caching.