Autonomous AI agents that perform tasks independently
Kunal Gupta
Autonomous, DSL-fluent coding agent built on the Claude Agent SDK — point it at any DSL directory and it plans, codes, debugs, verifies, and self-extends.
...morePatrick Espino
Expose Glyph Protocol glyphs as OpenAI Agents SDK tools
Disciplined multi-agent AI software factory: brief -> PRD -> RFC -> task DAG -> reviewed code, with human gates and a hash-chained audit trail
...moreHernán Inverso
Static budget certificates for LLM-agent workflows (LangGraph / CrewAI / OpenAI Agents SDK). Backed by a machine-checked (Lean 4) cost-soundness theorem.
...moreGitHub Actions
OKed plugin for OpenClaw. Gates skill and tool calls behind a human approval push to your phone.
fatelshardtodisobey
Kibana log query CLI for AI Agents - search and aggregate logs through Kibana Console Proxy with JSON-by-default output
niuzhiwen
Autonomous coding agent based on Loop Engineering principles — convergent feedback loop from requirements to delivery
GitHub Actions
Figs CLI — publish your AI agent's state to Figs (figs.so). Run by the agent.
GitHub Actions
Local knowledge server for coding agents — fresh docs and articles on demand via HTTP
kickitai
Scaffold a Claude-powered AI agent stack on any messaging channel — WhatsApp, Telegram, Discord — using your Claude subscription. No Anthropic API key required.
...moreamong_robots
Browser-native testing harness — a QA agent that drives a real browser like a user and returns a pass/fail verdict with commentary
...more2salley
Typed client for 2s.io — pay-per-call AI agent APIs on Base or Solana via x402.
jfeilberg
Scaffold a Slack-native AI agent in one command.
omar-azam
Forge Agent — Autonomous AI coding via browser automation. No API key needed.
Structured, provenance-aware knowledge layer for Python applications and AI-agent workflows
linghungegeg
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
osovv
Portable OpenCode workflow toolkit — 6 plugins, managed agents & skills, a spec-to-code pipeline, security, and the vvoc CLI.
...moretelus-labs
Run your AI coding tool through a 17-stage dev pipeline. Multi-host across Claude Code, Codex, and Gemini CLI. Artifacts and gates on disk, not a chat log.
...moreKun-0546
Goal-driven harness experiments on real agent runtimes — a local, stdlib-only CLI workbench with Copilot + Auto modes and evidence-first reporting.
...moreajmd17
Agentic coding with local LLMs or BYOK (Bring your own key)
verigentai
Verigent trust verification for the Claude Agent SDK
verigentai
Verigent trust verification for Microsoft AutoGen multi-agent systems
"Charles C. Figueiredo" <[email protected]>
Local-first agent memory: an Obsidian markdown vault as source of truth, with a rebuildable DuckDB index.
Arm <[email protected]>
Framework-agnostic tools for Device Connect — discover and invoke IoT devices over NATS/Zenoh