The #ai-agents leaderboard on RepoRanker surfaces open-source repos tagged ai-agents on GitHub, with listings that remain discoverable after launch day. Top puts placements first by total, then other repos by GitHub momentum. Search matches are ordered by relevance first. Funding sources are shown on each placement.
Browse to find ai-agents projects worth contributing to, or list your own ai-agents repo for free. Search these repos, or choose New to sort by submission date and filter by time.
OpenClaw plugin for AI agent runtime control — enforce LLM cost limits, tool call caps, action permissions, and audit trails on OpenClaw agents before execution
Centralize and secure MCP servers without worrying about the file-sharing problem.
Phone/browser workbench for tmux-backed AI coding sessions
Composable TypeScript toolkit for AI agents: 25 packages, 140 providers, 5,000+ models, and zero lock-in.
Accountable Autonomy: open-source evidence layer for every autonomic action and writes a hash-chained record an auditor verifies offline, without trusting you.
The best AI harness you can run yourself.
Enverif transforms into a dynamic, Open Claw-inspired sales management platform. Select an @agent, assign a @plugin, @skill, or @workflow AI with handle entire.
Memory for Claude, Codex, Cursor, and any MCP agent. Free locally or $10/month managed.
Adaptable, accountable AI teams. Visually
Declarative multiparty session protocols for AI agents: the protocol owns control flow, the model only fills typed payloads
10xScale Agentflow is a lightweight Python framework for building intelligent agents and orchestrating multi-agent workflows. It's an LLM-agnostic orchestration
Self-hosted server that enforces hard limits on AI agent spend, risk, and tool actions before execution. Reference implementation of the Cycles Protocol
Drop-in @Cycles annotation that enforces budget and action limits on Spring Boot AI agents and LLM-calling services.
Tokio-native Rust client for the Cycles protocol — runtime authority over autonomous AI agents. Cycles enforces hard limits on spend, actions, pre-execution.
TypeScript/Node.js SDK for AI agent budget governance — enforce cost limits, tool permissions, and multi-tenant policies before execution.
Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, action permissions, and audit trail.
MCP server that gives any MCP-compatible AI agent (Claude Code, Cursor, Windsurf, custom agents) runtime budget, action, and audit authority.
Python SDK for AI agent budget governance — enforce cost limits, tool permissions, and multi-tenant policies before LLM calls or agent actions execute.
KodeAgent is a minimalistic approach to building AI agents. It's designed to be the robust reasoning core inside your larger system, not the entire platform.
Inspect any x402 endpoint before you pay it.
Agentic Orchestrator built with Enterprise-Grade Security. Seamlessly bridging Gemini with Auth0 Governance and to act on your behalf—securely and autonomously.
Free listing, live immediately, and it stays discoverable long after launch day. Paid placement is optional and starts at $3.