Autonomous AI agents that perform tasks independently
brendanpro
Agent Development Kit for Node.js - A flexible and modular framework for developing AI agents
benoit-at-makkr
Pattern execution engine — runtime-neutral core (Web-standard APIs only).
artificer-innovations
Web chat interface for NanoClaw AI agent framework
alexngai
Multi-agent coding agent CLI: one agent is a tool, N coordinated agents are the product. Built on Anthropic's Claude Agent SDK with swarm/team orchestration, multi-provider support, and a Bun-native interactive TUI.
...morefosterg4
Delegate tasks to specialized subagents with isolated context windows, structured JSON handoff, contract schemas, and live TUI streaming
...moresentinel-agent-sdk
Non-blocking AI agent event logging for compliance teams
Claudio <[email protected]>
Agente autônomo de programação via terminal com IA
agentmount contributors
Make a FastAPI app agent-ready in one line.
floelabs
A local budget guardrail for AI agents — hard-stops your agent before its next LLM call crosses a USD ceiling. Vercel AI SDK middleware.
...moreJordan Baillie
An independent significance referee for LLM & agent evals — is your improvement real, or noise?
astatus contributors
Local agent status reference implementation
Knowledge/recall/grounding sense for AI agents — knowledge graph + RAG that grades citation-faithfulness and groundedness on the agentsensory verdict contract.
...moreJakeJunior1
Wake me when you need me — A disciplined, drop-in Claude Code framework that grows with you.
MarzWars
Oculus AI — A memory-first, uncensored AI workspace for digital agencies. Persistent memory, interactive code sandbox, file intelligence, and real workflow tools — built for getting actual work done.
...morentholm86
AI governance framework built on three architectural principles: Commander's Intent, Observable Autonomy, and Convergence Is Silence. Defines Autonomous Reasoning Fidelity (ARF) as the target property.
...moreFrank-Pu
Configure an AI digital employee in 25 minutes. Runs on YOUR Claude Code / Codex / Kimi / GLM CLI. Auto-installs into launchd. Configuration is the moat.
...moreprasenjeet-symon
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
...moreShiningYangYXN
基于Node.js的轻量版元宝Bot客户端
songyang753-cloud
🏠 小绿管家 · 全本地家庭感知 Agent:端侧摄像头感知(人脸/动作/跌倒/声学)→ 级联语义漏斗 → 可插拔 LLM 决策(Claude/Ollama)→ 主动通知与设备联动。隐私优先,视频不上云。
End-to-end agent testing — assert an agent's tools fired, via Revefi LLM observability
ngoquan0904
One-command distribution for the datn multi-agent assistant (hides docker compose).
Multi-agent adversarial review & deliberation for plans/specs on subscription CLIs (reduce rework before execution)
Measure how DSPy prompt optimization affects the prompt-injection robustness of agentic LLM programs, using AgentDojo's attack suite.
...moreNous Research
Open-source multi-agent orchestration CLI — spin up a 5-role AI team with automatic topology selection, model freedom, and white-box observability
...more