Autonomous AI agents that perform tasks independently
chless
Scaffold a self-improving agent governance framework (meta-skills, hooks, memory hierarchy) for Claude Code.
Official Python SDK for Attestify OS — governed agent execution, x402-native payments, EIP-712 reputation credentials, escrow settlement, RAG semantic memory, predictive drift scoring, fleet health, and immutable receipts.
...moreGoldentrii
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
CallesnikovProduction
Experimental local-first Android AI agent built with Kotlin and Jetpack Compose, featuring on-device Gemma models, policy-controlled tool calling, and safe Android automation.
...morehhdhh
Multi-agent control plane for cross-border e-commerce: LangChain + Claude ReAct workflows, RAG, and ERP/CRM-style tool integration. 跨境电商多 Agent 调度中枢：LangChain + Claude + RAG + ERP/CRM 工具集成。
...moreHabitat-Thinking
A full-day hands-on workshop for building safe, explainable, domain-grounded AI agents — a goal-oriented Embabel (Java) conference-planner you grow across before/after lab branches, with a Diátaxis docs site.
...morewangyuahn
Loop-core multi-agent coding tool that orchestrates work through plan→implement→review cycles. The orchestrator is read-only — it searches project memory, enforces custom rules, and delegates all code changes to parallel swarm sub-agents. Built on Kimi Code CLI (MIT).
...morenavig-me
Local-only, agent-agnostic marketing/outreach skill: SQLite CRM, file-approved sends, SMTP.
kanglongh
LLM Agent · SCA 安全约束 · 跨域故障诊断自主探索
ferdinandl007
macOS computer control CLI for AI agents & OpenClaw — control any app on your Mac using natural language labels. Powered by OmniParser v2 (YOLOv8 + Florence-2). Click, type, scroll, screenshot & automate anything.
...moreUnifyApps
Lightweight OpenTelemetry wrapper with UnifyApps-aware defaults for tracing LLM/agent applications.
jens-duttke
Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.
...moreDDHH
A tiny, readable circuit breaker for LLM calls: hard budget caps that fail over to a free local model instead of raising or overspending.
...morepaahaad
AI agent skill for the Solduino Arduino/ESP32 Solana library. Installs into Cursor and Claude Code skill directories via npx.
...moreaymwoo
A plugin-driven Educational OS / LMS platform with AI agent teaching assistant
wonsukchoi
A public directory of pre-made, agent-editable cron jobs.
mthanh
Vesper Agent Suite — CLI to manage AI agents, prompts, instructions, and skills for GitHub Copilot (VS Code) and Claude Code
...moreGitHub Actions
Contract work in an enclosure: a Claude Agent SDK agent whose only tools are the contract-ops suite — no shell, no filesystem, no signing.
...moreedumeson
Ralph Loop - Autonomous 9-phase feature development with spec-driven design, agent-browser E2E testing, and memory system
...moreplqws
Session runtime and transport-neutral client and server protocol for Demi.
artickc
Control OpenAI Codex CLI from Telegram over the codex app-server protocol. Switch projects, resume coding sessions, stream responses with diffs, queue follow-ups, and run 24/7 as a cross-platform background service.
...morepablof7z
Install reusable agent profiles into Codex, Claude Code, OpenCode, Goose, and tenex-edge.
Core messaging and memory service for the AGAPES Homonoia Multi-Agent System framework
AgentLatch Contributors
Zero-dependency, terminal-native Python middleware for resilient and observable AI agents.