Autonomous AI agents that perform tasks independently
itchenshi
DeepSeek Harness 桌面壳 —— 内嵌 Web UI、自动保持最新引擎、自带数据目录管理与系统托盘。
Tencent Cloud CLS Team
CLS observability SDK for LangChain/LangGraph — 6-layer span hierarchy, direct upload to Tencent Cloud CLS
Durable, self-healing multi-provider LLM gateway and circuit breaker with autonomous failover, tool idempotency, and context compaction for AI agents (Claude Code, Hermes, OpenClaw, OpenCode).
...moreThor Whalen
Look astern: mine your past Claude Code sessions for recurring problems, friction, rewritten code, and the vocabulary gap between you and your agents
...moreGitHub Actions
AI-agent skill: build Mosaic Pro (Nextend) WordPress sites by writing the underlying data model directly - 23 custom tables, no visual editor, no DOM. Every node type, style property and node property swept against a live install and asserted on the deliv
...morech4r01teer41
Chain of custody for AI agents: signed, independently verifiable receipts for tool calls. MCP gateway + Cedar policy + Merkle transparency log
...morebuddhilive
System prompt assembly registry for the DeepSeek Harness
rs25-labs
Private, local-first memory subsystem for the pi coding agent. Long-term memory across sessions, stored on your own machine in SQLite, with optional on-device semantic search. No server, no cloud, nothing leaves your machine.
...more7resp4ss
No-summary context-window rollover for Pi with durable notes checkpoints, history recovery, and a post-fallback tool-call fence.
...moreGitHub Actions
Conversation-first plugin discovery and lifecycle management for DeepSeek Harness.
GitHub Actions
Local cockpit for running and tracking AI agent tasks in your repo. Uses your logged-in `claude` CLI and `gh` — zero config, zero database.
...moreGitHub Actions
Provider-neutral connector SDK for Showrunner agents
Mrbaeksang
Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.
...moreHarcoChen
DeepSeek Harness (DSH) for VS Code — AI coding with native diffs, tool approvals, persistent sessions, and Trace insights. | AI 编程助手：原生 Diff、工具审批、持久会话与 Trace 分析。
...moreAlunixa-Code
Alunixa X — cross-platform AI Agent Control System for models, providers, tools, automation, connections, themes, and Codex desktop runtime.
...moreVaEmail (Agence SW)
Email infrastructure for AI agents and applications: send transactional email, authenticate sending domains, track delivery, diagnose deliverability.
...moreThe Jeffy Loop: an autonomous audit-and-fix loop for Claude Code, with proof.
hklee128
Multi-agent project definition & QA framework for Claude Code — Socratic dialogue, behavioral testing axes, design intent, orchestrated review
...moreGitHub Actions
Focused code retrieval, editing, safety checks, and language-server support for Pi.
Adversarial Coding Agent Arena — contamination-proof LLM coding benchmark
NovaOS Team
Python client library for connecting to and communicating with AI Agents that implement the Agent Communication Protocol (ACP)
...moreCandyChain <[email protected]>
Official Python SDK for the CANDY AI Marketplace - deploy an AI business in 3 lines of code.
Tom Vaucourt
How many agentic-coding users a local LLM deployment serves: capacity model, CLI and live-endpoint hypothesis tests
Multi-agent orchestration for EggAI