Autonomous AI agents that perform tasks independently
Veedubin
Bootstrapper CLI for the neuralgentics OpenCode plugin
Garrett Masters (G Talks Tech)
Hardrails reference implementation: a bounded network agent. Deterministic boundaries around a non-deterministic agent.
SJK Systems <[email protected]>
Deprecated. ClevAgent is no longer distributed as a Python SDK. See https://clevagent.io
Moxie contributors
Moxie — the open-source money agent that acts on your money, only with your approval. Local-first, consent-first.
icculusc
Framework-agnostic prebuilt LangChain tools for agents (works with any LangChain/LangGraph app)
pace
Governed-knowledge retrieval + injection for LLM agents -- concepts, playbook entries, three-scope shadow merge, and before_model middleware
...morepace
Tool framework for LLM agents -- routing, execution, and builtin tools
Ahmad Farhan Ishraq
General purpose agent harness inspired by Claude Code
Unison (万物一心) — Loop Engineering pipeline for multi-agent collaboration
metaspartan
Cybara - Your agents. Your tools. Your runtime. Harness the power of AI
clark1015
An AI strategy consultant (Claude Code agent) that interviews you instead of answering — structured, hypothesis-driven problem solving compiled into a working agent.
...moreRobbieXie
A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架，通过 LangGraph 驱动的会话控制与任务切换，连接结构化工作流引擎与推理型大模型智能体。
...morelubluniky
A complete LLM agent in ~200 lines of C++ on an ESP32-S3
Harnessie: a brain-agnostic multi-agent harness (orchestrator / workers / verifiers) with verification gates, consent-based orchestration, ownership lanes, adversarial decision records, routing policy, and a tamper-evident audit log.
...moreExport Claude Code token usage (per agent/model) to Prometheus, OTLP, or stdout -- parsed from transcripts, works on Max/Pro subscriptions.
...moregulei
Move and install AI agent skills between Claude, Codex, Cursor, and project scopes.
joshuaknauber
ORM + Access Control Layer for AI Agents
raffx
v0.6 signing-time gate for Solana: decode any base64 tx offline, classify 37 danger primitives + Native Stake + bounded ATA/Memo recognition + a 14-program DeFi/NFT clear-signing registry, resolve ALTs and clear-sign Squads proposals with --rpc, optionall
...morebekasbah
KasbahOS — govern any AI agent in one line. Cryptographic receipts, multi-layer threat detection, drop-in middleware for OpenAI, Anthropic, LangChain.
...moremisakago
Browser automation CLI for AI agents
Hada Kang
Decision-stability measurement for LLMs: run the same decision N times, get a flip rate with a bootstrap CI, and compare models against their own noise floor.
...moreA flexible multi-agent orchestration framework with configurable agent and tool registries
ship
Decompose a task with Codex and dispatch the subtasks to Jules.
Aditya Vinodh Arjun <[email protected]>
Python SDK for agent-runtime — invoke declarative agent workflows from Python