[ICLR '2026] Native Reasoning Models: Training Language Models to Reason on Unverifiable Data

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Code for aladynoulli

Open Science is an open-source, local-first, model-agnostic AI research workbench with scientific agents for reproducible research and discovery.

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Agent Framework and Runtime

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native…

The open-source AI workbench for scientific research

Scalable RL for Any Agent and Sandbox.

Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally

An AI research Agent for scientific innovation.

AgentGuard: Zero-Trust Security Foundation for AI Agents

Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

Agentic RL on Any Harness at Scale

A framework for building agent environments for RL training and evaluation with Strands Agents.

Synthetic data curation for post-training and structured data extraction

HarnessX is a harness foundry: forge any number of agent harnesses from reusable processors and bundles, pair each with any model, and evolve them through training.

中国科研常用LaTeX模板集

KDNA protocol and Core runtime for versioned, verifiable, encrypted, authorized judgment assets.

Offical implementation of "Life-Harness"

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills b…

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/O…

Orchard: An Open-Source Agentic Modeling Framework

eBPF Information Flow Enforcement for AI Agent safety, security and effectiveness