Autonomous AI agents that perform tasks independently
Kendra Laboratories Limited
Durable multi-agent execution kernel: Pregel BSP supersteps, Temporal durability, typed compiled signatures.
mgordgda
Report agent state to the FlashyOS mesh — the DeAI Operating System for Agentic Autonomous Organizations (AAOs).
jinyuanwang
Command-line AI agent powered by Kimi K3 — chat in your terminal, it runs real system tasks
Ashwin Mathur, Varun Mathur
Pointer to the pypi package `agentic-graphrag`
Failproof AI <[email protected]>
Emit agent telemetry to FailproofAI Cloud — zero-dependency, stdlib only
Pairwit <[email protected]>
Pairwit — consent-first coding agent (placeholder)
Shubhs5758
Watch your multi-agent AI workflow as a 2D retro pixel-art game
acarmisc
kagent (Kubernetes-native agent runtime) invocation module for the ai-agents Backstage backend plugin.
WSL043
ChatGPT/Codex subscription provider for DeepSeek Harness with OAuth, models, quota, search, and image tools—no API key or Codex CLI.
...morelezi-fun
Unofficial local and LAN WebUI for the real Codex app-server, with approvals, streaming tools, review diffs, and mobile support.
...moreZTCNO0NE
Loom (织机) — external coach / second verifier for DeepSeek Harness: silently evolves your agent's tools, skills, config and model, with deterministic verification and cold-apply.
...morestaff-os
An enterprise workbench for the DeepSeek Harness: AI employees, knowledge bases, skills, MCP servers and DSH plugins, all manageable from a running session.
...moreLxxz666
DeepSeek Harness 的 Python 重实现：插件内核 + 事件溯源 + 五段工具管线 + wanter（water+ant）物理经验层——纯梯度 0% 逃逸 vs wanter 100%，路径复用 ≈30× 加速
LoopSkill
Skill-portability CLI: import/diff/pull/apply across AI-agent skill directories. import/diff are offline by construction — no account, no network.
...moreKai-Chun Hu
What a provider and funduq agree on, from the provider's side: identity, the ports, and the provider's own worker loop — for an agent provider, or an LLM provider with the `llm` extra
...moreLeeminjing
DeepSeek Harness plugin: auto-repairs invalid tool_calls/tool message pairing in the messages array to stop 400 INVALID_REQUEST session crashes.
...moreCaYatur
Capable coding agents on local Ollama models — including the small ones. Task-based model routing, tolerant tool-call parsing, and an auditable permission system.
...moredevashish_sharma
Modular CLI tool featuring LangGraph AI Agent, file compression, string manipulation, and API integrations
jerryjiao
Agent-native Markdown workspace for raw capture, linked wikis, knowledge graphs, and semantic search
GitHub Actions
四川大学校园服务命令行工具（教务/微服务/缴费/体测/第二课堂），面向 AI 代理与脚本设计
er_sunny.04
General-purpose local-first AI agent platform with tools, memory, automation, research, multi-agent orchestration and Gemini Live.
...moreidan-actionproxy
TypeScript SDK for governing AI agent tool calls with ActionProxy policy, human approval, one-time grants, and audit
bramatom
Intelligent AI Agents for every development task using OpenRouter API
petebellis
Earn USDC answering real support tickets. Your AI agent reads an open bounty board, drafts an answer, pays a few cents to submit it over x402, and gets paid when a human approves it.
...more