Autonomous AI agents that perform tasks independently
Cytario
CLI for working with Cytario storage connections as the signed-in user (browser OIDC sign-in, AWS CLI profile setup, token refresh)
...morebigfish1913
Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin ABI
...moreW-SCHOLAR
Cursor for the physical world, Connecting AI to the physical world. 物理世界的Cursor，连接AI与物理世界
nibzard
A celld-native AI agent framework — one agent per cell, alarm-paced bounded steps, no platform or model lock-in.
alhermann
openPASO — open Platform for Agentic Simulation and Optimization. An AI agent that operates nine finite-element and multiphysics codes through one interface.
...moretronicum
Read-only, local-first token usage and budget-runway tracker for AI coding agents (Copilot CLI, Claude Code, Codex CLI, Gemini CLI, Hermes Agent, ...) plus a local-vs-cloud savings estimator
...moremiui666
berry-agent 类型化 SDK 客户端——spawn serve stdio / 直连 HTTP 两传输适配，事件类型面自仓单源
GitHub Actions
TypeScript SDK for Mandala Computer — cloud desktops for AI agents
alexkahndev
JavaScriptCore-native sandbox for Bun — heap-isolated execution for untrusted code, isolated-vm-shaped API
GitHub Actions
OpenTelemetry-native tracing for AI agents and LLM applications
Charles Tabor
pH core: the cordis plugin subset, the session log, the LLM vocabulary, and the agent loop.
AuditAgent
Drop-in logging, human approvals, and compliance evidence for AI agents.
ahmedsayed1911
Local-first AI-to-3D pipeline: LLM planning, validated Blender generation behind an MCP tool boundary, read-only vision review, semantic motion, and GLB/MP4 export with a FastAPI + Three.js studio.
...moredefinableai
A minified agent core: the infrastructure to run an agent, under 2000 readable lines of stdlib Python.
xmor
ARA — Agent Runtime Architecture: Java 21 framework for building autonomous AI agents and multi-agent systems. LLM integration, tool calling, deterministic I/O contracts, RAG and human-in-the-loop. On Maven Central (io.github.xmor).
...moreAmanjot Singh
Deterministic, LLM-free runaway detection and circuit breaking for AI agents.
Oh-dong-kyu (Cantor Labs)
Deterministic 30% zero-loss token slimmer middleware for multi-agent LLM systems [Binary Sealed].
liy
Shared component catalog, JSON renderer, and Mote query integration for agent-authored interfaces.
Andreax
Pure Python client (no LangChain) for Andreax's pay-per-call x402 AI tools (USDC on Base, EIP-3009 autopay).
Merge Gateway CLI — route your coding agents (Claude Code, Codex) through Merge Gateway
Local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents: 57 providers, fallback routing, credential health, a native web-search tool proxy, and analytics with cost provenance
...moreArmin Zou
Wires project Brainspaces and skills into coding agents.
PerceptEye
Self-improving agents through continual learning: in-process agentic RL that turns your own agent's work into training data. Observed tool outcomes, outbound-only, one runtime dependency.
...moreairprompter
Run prompts and workflows approved in AirPrompter on your own systems: signed pull-only updates, an encrypted restart-safe slot store, offline operation, content-free telemetry.
...more