agent-framework

Multi-agent orchestration for Orca, as code — LLM-authored plans that fan out worker agents.

Cosight — A realtime multimodal AI agent runtime with composable roles and capabilities.

A small programming language built end-to-end by an autonomous agent fleet on the cheapest available model — 95.4% mutation-tested, merge-on-green PRs, every claim published. Complete; archived.

Minimal Node.js agent loop for Ollama: local LLMs that read/write/edit files, run shell commands, and call MCP tools. MCP client and server, two dependencies, fully offline.

Shared instructions, workflows, conventions, and memory for AI agents — across teams, projects, and functions.

A disciplined multi-agent dev team for Claude Code — guild of specialist agents, a 4-phase decision contract, and token-budget discipline. For complex, multi-feature codebases.

AI agent command center with built-in security. Ground truth verification, hash chain audit trails, credential isolation.

Organization profile and public entry surface for Riverbraid.

Execution bridge from verified state into system action surfaces.

Production-ready AI dev workflow scaffold with 59 skills, 33 agents, hooks, and rules for Claude Code, Codex, Gemini CLI, Copilot CLI, Qwen Code, and OpenCode.

Self-describing UI framework for AI agents — 50 Material Design 3 web components with runtime introspection

From one prompt to a finished product — fully autonomous. Auto-plans, remembers across sessions (persistent context), builds end-to-end, audits security & performance, deploys. 18 agents + 39 workflows for ChatGPT, Copilot, Codex, Cursor, and other AI coding tools. Built by NexVar.

Topic-Scoped Virtual Context — context isolation for persistent AI agents. Treats conversation topics as virtual processes with independent lifecycles.

Production multi-agent orchestration framework - Claude Code, CLAUDE.md governance, multi-tier model routing, token economics

开箱即用的 OpenClaw 多智能体工作区 · Turnkey OpenClaw multi-agent workspace — clone, configure .env, run deploy. Zero hardcoded paths. MIT.

AI-native desktop command center built on top of DeepSeek Harness

A framework-agnostic catalog of reusable AI agent definitions, orchestration patterns and adapters, with CLI tools, exports and visualization.

The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension · Anki export · MCP server · runs on Ollama

An open-source AI runtime framework focused on task execution, traceability, and delivery closure.

Modular agent infrastructure primitives for orchestration, memory, routing, cost tracking, and AI system operations.