Autonomous AI agents that perform tasks independently
Faye-labs
把操作手机点外卖封装成给 AI agent 调用的工具——文本进文本出(markdown表格)、对非视觉/远程 LLM 友好、可 MCP 封装或原生 tool 直用。基于 Open-AutoGLM。
NekomyaDev
Nudge — a typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript. Traces as tests, MCP tools, A2A export, LSP, OpenTelemetry.
...moreKeeps registered constraints present in LLM agent context across compaction, and classifies what the summariser did to them.
...moreDEPRECATED: multideck was renamed to magent. This shim installs magent-multi-ai-agents-manager.
Haebin Na
Locally running chat agent with access to Claude Code, Codex, and bash
A resumable multi-agent pipeline that researches, writes, judges, narrates, and renders short-form YouTube videos for any niche.
...moremaxjustships
Local-first, agent-driven evidence and verification for public website surfaces.
GitHub Actions
Playwright browser harness for AI agents: controlled native tools, sessions, screencast, and optional Docker browser sandbox.
...moreKıvanç
The personal OS that grows with you - mood, sleep, nutrition and habit tracking with pattern detection, built for Ollama/OpenAI/Anthropic/OpenRouter.
...moregreg-asher
Typed Vercel AI SDK presentation adapter for Kestrel runner streams
jamestexas
DPoP (RFC 9449) utilities and resource-server verifier SDK for notme-issued access tokens. Zero dependencies, pure Web Crypto — runs on Cloudflare Workers, Node, Deno, and browsers.
...moreAndy Yaro
Local-first orchestration runtime for multiple autonomous coding agents (Claude Code, Codex CLI, Gemini CLI, and more) collaborating on one software project.
...moreVystak chat channel — OpenAI-compatible unified chat endpoint routing to agents
Keviqai
Open-source control plane for AI agents in production — task orchestration, artifact provenance, human-in-the-loop approvals, RBAC. 15 microservices, 21 verified user journeys. Docker Compose up in 60s.
...moreTrey Herr
Deterministic tmux relay/dedup daemons for AI-agent fleet monitoring
Yauhen Yakimovich <[email protected]>
Deterministic project bootstrap and control CLI for AI-assisted development: grem stamps structure, agents do the work.
Evidence-first reconciliation for irreversible AI-agent actions
carloscortezcloud
Minimal provider-agnostic AI agent framework. Tool loops, budget control, multi-model routing — in 200 lines.
frierensz
n8n community node for DeepSeek V4 (chat + reasoning) with an AI Agent chat model sub-node
mfinikov
sup — a messenger for AI agents. Thin CLI over the sup network (agent-to-agent text messaging).
Responsible AI
Agent Control Specification: a stateless policy decision runtime implementing the agent-hooks interceptor contract.
Ahmi
Self-improving multi-channel software coding agent framework (memory, learning, tools) — not a medical product
Ramprasad Gaddam
Sign OpenAI agent tool calls with Vouch Credentials.
Vinicius Vale
Model-transport layer for the Cogno cognitive pipeline — LLM + embedding backend protocols, Ollama + cloud backends, a single-backend factory, and a resilient fallback chain
...more