AI agents

OpenHands is an open-source software development agent platform that can edit code, run commands, and interact with tools.

A local-first CLI and dashboard for running autonomous digital-twin agents across social platforms, with content workflows, scheduling, and browser automation.

Opus Manager is a Claude Code skill that makes Claude the manager of a coding project: it writes tickets, dispatches them to cheaper coding agent CLIs on your machine, reruns the acceptance checks itself, and has a model from another vendor review the change.

A self-hosted coding agent that takes labeled GitHub issues through planning and implementation, opens pull requests, checks changes against acceptance criteria, and merges when configured gates pass.

Orkas is a local-first desktop AI team where a commander coordinates specialist agents and local coding-agent runtimes, with support for user-provided model providers.

A command-line client for managing prospects, sourcing, campaigns, and sales outreach through the Overloop API.

A web app that monitors Polymarket and Kalshi markets, detects configured price, volume, and wallet signals, and provides LLM analysis of alerts.

An open prediction-market benchmark and starter template for building autonomous AI trading agents.

A Python framework for building and running AI agents with integrated tools, controllable reasoning, memory, security, governance, and observability.

Quorum lets multiple AI models and agent CLIs conduct structured debates using formal methods, critique, and synthesis, through a terminal UI, MCP, and a web version.

Raven is an open-source host agent that plans complex tasks as DAGs and orchestrates built-in research, coding, design, and on-call agents plus third-party agents such as Claude Code, Codex, OpenClaw, and Hermes Agent over ACP, CLI, or OpenAI-compatible APIs.

A self-hosted Telegram agent that analyzes social-media videos, returns source-linked breakdowns, and can plan or build related projects on the user's PC with command approvals.

An async HTTP client for autonomous agents that handles HTTP 402 payments across multiple payment rails, enforces spend policies, recovers credentials, and emits audit traces.

A Rust research prototype for LLM runtime and agent control, with routing, memory, runtime adapters, rollback, tracing, and gated self-evolution.

SandBase Harness is a self-hosted AI agent runtime and MCP bridge for persistent sessions, sandboxed tool execution, credentials, audit logs, and replay. It supports local and container-based execution backends, whose isolation properties differ.

Screenpipe captures screen and audio locally, then exposes searchable work history and agent context through an MCP server. It supports scheduled agent workflows and per-pipe access policies, with processing options that include local and configured remote models.

An open-source encyclopedia where agents generate, revise, and review knowledge articles, then explore connected topics through a knowledge graph.

solveathome is an MIT-licensed framework for running a swarm of AI agents owned by different people against one open problem, with public transcripts, peer review by other contributors' agents, and a small group of trusted reviewers who decide what is accepted.