Autonomous AI agents that perform tasks independently
xiaordong
从零构建 AI Research Agent：5 阶段渐进式学习，掌握 Agent Loop、Tool Use、Memory、Plan-and-Execute、生产增强。Python + GLM-4.7 + SQLite
SatyKrish
Reference implementation of a Databricks-native document intelligence agent with cited answers.
wadekarg
Upload a book. Change one thing. Watch AI versions of the characters argue about an alternate ending.
lislegenusthiobacillus199
Generate ComfyUI custom nodes for Foundation-1 to create structured text-to-sample music with fast, local audio diffusion workflows
...morejeanlag1
Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent PTY shells, sub-agents, planning, hooks, prompt caching, rate-limit-aware retry, mid-turn-checkpointed sessions. Anthropic + OpenAI.
...moreFilip Wojcik
Graph-backed knowledge extraction and agent memory for LLM systems
Pluggable Agent Framework — assemble multi-agent workspaces from composable layers
Toni Kukurin
Skill composition for LLMs — like lambda calculus, but the functions talk back
Upstream intelligence for AI coding agents — keeps CLAUDE.md in sync across your entire repo graph
NoBias Team
Comprehensive bias detection and mitigation for datasets, models, and LLM agents
GitHub Actions
Toolkit for testing and evaluating AI agent skills
channinglua
Open-source coding agent runtime — test-verify-fix loops, persistent memory, multi-model orchestration
lesquel
Remote control web dashboard for OpenCode — multi-project tabs, live SSE streaming, mobile-friendly, push/Telegram notifications, tunnel for phone access from anywhere.
...morefrancoara
Anthropic Messages API provider for Pacta
eizo__void
Local web UI for openclaude / Claude Code — claude.ai/code-style chat in your browser, runs on your phone or laptop. Spawns openclaude or claude as a subprocess and streams events over WebSocket.
...moreEvalGuard SDK — canonical alias for evalguardai. The independent AI platform for teams shipping LLM agents.
xingsy97
Agent Client Protocol framework and runtime for launching ACP agents, managing auth and permissions, normalizing session events, and building agent clients on top of @agentclientprotocol/sdk.
...morevalerio_amirani
Zenovay CLI — AI install wizard + full terminal analytics dashboard
GitHub Actions
Hold a key, hover, click — grab any element's source context for AI agents. Astro devtool.
hathbanger
RFC 9421 HTTP Message Signatures for AI agents — crypto primitives for Visa Trusted Agent Protocol (TAP)
Adi Bisoyi
Local-first context memory engine for AI-agent workflows.
UMAI
Python SDK for UMAI Agent Mesh Governance and guardrails.
A stateful personal agent with episodic memory for Claude Code.
A Textual TUI for managing Claude Code sessions