Autonomous AI agents that perform tasks independently
Trace-grounded CLAUDE.md adherence auditor: which prose rules your agents actually ignore, ranked from run history
michaelmanley
Badgr Agent CI — AI CI failure diagnosis for GitHub Actions, Azure Pipelines, GitLab CI, Jenkins, and Kubernetes. Explains the likely cause, quotes evidence, and suggests a fix.
...moresecurity holding package
artickc
Control Kiro CLI from Telegram over the Agent Client Protocol (ACP). Switch projects, resume and attach to live coding sessions, stream responses with diffs, queue follow-ups, and run 24/7 as a cross-platform background service.
...moreAttention Labs
Python SDK for SAA, the addressee layer for voice agents — device-directed speech detection that emits a turn_ready event per addressed utterance, so only speech meant for your agent reaches your STT, LLM, or TTS.
...morefraQtl
Local/offline audit for AI security-agent traces: repeated tool-output work, stale replay risk, and token-savings reports.
...moreML Arena <[email protected]>
Python SDK for ML Arena - submit agents, manage competitions, courses, and view leaderboards
Pure-Python Claude Code routing gateway
Local Multi-Agent Repository Intelligence System
babyblueviper1
Off-chain verify/recompute layer for the trustless-ai boundary chain: commit-before-outcome, anchor to public sources, verify any layer's claims trusting no one.
...morew25x80
Reusable proof profile, report, graph, and witness-planning primitives.
Fusion-Data-Company
All hustle. No luck. One database. Open-source agent-native business OS — bring your own AI agent. CRM, ops, finance, content. 234 MCP tools.
...morelml2468
Cross-platform agent gateway: a zero-cgo Go daemon (octobuddy-daemon) drives coding-agent CLIs — Claude first — into one normalized event stream, with a Wails v3 + Svelte desktop app on top. Multi-bot, per-session sandboxing, prompt-injection defense, skills, IM connector.
...moreNotASithLord
The first AI agent harness native to the browser. A Chrome/Firefox extension that runs the agent loop in your browser — drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK · no backend · no telemetry.
...moreAsim Awdah
One command to make your codebase AI-agent ready.
Production-grade plug-and-play memory for AI agents. Zero config, single-file storage, framework-agnostic.
Biologically-inspired dynamic memory layer for RAG and multi-agent systems
jasontendies
Slack automation CLI for AI agents
GitHub Actions
SELAT agent payment skill for discovering, ranking, and paying x402 / MPP services with Circle Agent Wallets.
maxmilian
Loop Engineering — a skill for designing & reviewing autonomous/semi-autonomous agent loops (Claude Code, Codex, Copilot, Gemini).
...moreGitHub Actions
Dispatch bounded coding tasks from your main AI agent to separate model pools, then verify the patches locally.
svlktv
Viktor — OpenAI-compatible bridge to the Viktor AI agent for OpenCode. By Valency Labs.
Artificer-Innovations
Web chat interface for NanoClaw AI agent framework
cryptocxf
Prompt Optimizer Skill — AI roundtable debate persona optimizer for OpenClaw shrimp. Creates anthropomorphic personas, debate constraints, and owner position expression for AI agents participating in panel discussions alongside human guests.
...more