#ai-agents

Pre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.

The identity provider for AI agents — registry, scoped delegation, in-path MCP enforcement, instant revocation, tamper-evident audit.

A fast, single-binary C database that gives AI agents durable, searchable long-term memory — with a Claude Code integration.

Chat with your LangGraph agent inside JupyterLab — a sidebar chat for any CompiledGraph

Autonomous AI programming. Stop babysitting your coding agents. You make the important decisions; AI does the rest.

The agent harness: sandbox any agent, verify each step by replaying it against real state, and keep a deterministic trace.

Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.

Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.

Factory AI: durable private coding organization with deterministic orchestration, isolated agents, Azure/Bedrock routing, memory, cost visibility, and gated delivery.

A local-first control layer for AI agents

Give AI proven facts — a cryptographically verified truth layer for agent AI, built on ZK proofs, selective disclosure, and on-chain provenance.

A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.

AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

Terminal code review for AI coding agents. Live diffs, comments the agent answers, PR review, MCP built in.

Spec-first development toolkit for agentic AI coding agents — skills + guardrails for Claude Code, Codex, Cursor, Antigravity, and more.

Open protocol and reference node where humans, their AI agents, and local LLMs share apps, knowledge, and capabilities. Self-hosted, federated, MIT.

Plan ? execute ? verify workflow automation for AI coding agents. One installer, five runtimes: Claude Code, Codex, Gemini CLI, OpenCode, Copilot.

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

A governed, local-first MCP development control plane for AI coding agents.

Model-agnostic design knowledge base + skill system for AI coding agents (Korean-market-fluent)

Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

Local-first control plane for AI coding agents: repo memory, verification, sessions, and dynamic workflows.

Run agents you don't babysit, and trust the result. awf runs agentic workflows with independent gates that check every step and resumes after crashes.

Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, and subagent roles — synced to Claude Code, Codex, Droid, Hermes, and Pi. Commit-pinned and audited.

One CLI to manage AI agent configs (Claude Code, Cursor, OpenCode, GitHub Copilot) from a single canonical store. Push to every agent, pull edits back, sync across machines via git.

Give your agent a spending limit it can't exceed. Non-custodial tabs on Solana, plus one-shot x402 across the major EVM chains. Buyer + seller SDKs.

EgisAI SDK

Telegram MTProto CLI for scripts and agents, powered by mtcute.

Allows AI agents (e.g., Cursor, Claude Code) to debug within Tauri apps via screenshot capture, window management, DOM access, and simulated user inputs.