Autonomous AI agents that perform tasks independently
Abhigyan Shekhar
Waggle — local-first semantic caching for LLM, RAG, and agent workloads
liketimes
Next-generation multi-agent harness with 6 specialized agents, presets, security guardrails, and audit trail
yuxuanliang
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness
GitHub Actions
A Symphony-compatible multi-provider task orchestrator and dashboard for DeepSeek Harness
atwize
CLI for local Postgres setup, connecting BD Agent backends, migrate, and doctor
shelbyvst
A dead man's switch for autonomous agent fleets. Finds the agents that went quiet, and the ones that lie about succeeding.
...morenoise01
Governed beliefs for LLM agents: an append-only ledger, SMT-checked consistency, defeasible revision, and calibration instruments.
...moreTaran Douley
Measure how often your LLM agent reaches for the wrong tool when it cannot ground an entity in a request.
nevodavid10
One-command bidding on agenticbid.lol — the pay-to-rank leaderboard for AI agents (x402 + USDC on Base)
Wytness <[email protected]>
Wytness — the blackbox recorder for AI agents. Customer-held PII keys, per-event Ed25519 signing, audit-ready evidence packs. Built on Microsoft's Agent Governance Toolkit.
...moreDan Barua
Inter-agent messaging bus for Claude Code, Grok, OMP, Codex and others
Loqira-Labs
The best AI harness you can run yourself. One file: web UI, tools, memory and orchestration built in. Run a team of agents across providers at once - lead on Claude, architect on GPT, researchers on DeepSeek. No sandbox, no skills, no MCP: a tool, not a nanny.
...morerejian2022
Android MCP bridge: phone state, UI control, Shizuku shell tools for AI agents | Android MCP 桥接：手机状态、UI 控制、Shizuku shell 工具，给 AI 客户端用
...moreLunaticLegacy
A homebrew Agent framework.
kenwoodjw
Microsandbox integration for Deep Agents
wwwroot
Modular AI instructions and autonomous engineering skills for Cursor, Claude Code, Windsurf, Copilot, and Gemini.
GitHub Actions
CLI tool for AI agents to control Windows Remote Desktop sessions
Pipeliner
Fail-closed evidence gates for experiments and AI-agent workflows
Waseem Ghanem
Deterministic, local behavioral and safety evaluation for AI agents
agent-ultra-kit contributors
Agent-agnostic adversarial panel, ULTRA build loop, command broker, and proof gates for AI agent systems
TimeTravel
Time-travel debugging for AI agents — OTel-in / replay-out.
MemorySync
MemorySync memory for CrewAI: a native StorageBackend for Memory(storage=...), agent memory tools, and recall context for tasks.
...moreA key-addressed retrieval system for coding agents
Marc Oakes
Works with any coding agent you can start from a terminal and any model behind an OpenAI-compatible endpoint: runs your repo's own gates, records the check red before the work, and refuses what it cannot evidence
...more