Open-Source

Most AI agents complete a task and forget everything about how they did it. Hermes Agent remembers — and then rewrites its own playbook. Nous Research today officially released Hermes Agent v0.8.0, the first stable public launch of their open-source self-evolving agent framework. This isn’t a minor version bump from the v0.7.0 feature preview that circulated last week. It’s the official Nous Research launch: production-ready, 3,496+ commits deep, with a live landing page, a growing community repository, and a model-agnostic architecture that supports any LLM endpoint you can throw at it. ...

The Agent Skills open standard just got a significant new toolkit. Felo Skills launched today as an open-source npm package that plugs real-time search, slide generation, web content extraction, social listening, and knowledge base capabilities directly into Claude Code, OpenClaw, Gemini CLI, and other coding agents — in a single install. If you’ve wished your AI coding agent could search the web in real time, pull structured content from any URL, or generate a slide deck from a prompt without leaving your workflow, this is the package you’ve been waiting for. ...

There’s a particular kind of tedium that every AI engineer knows intimately: the prompt-tuning loop. You write a system prompt, run your agent against a benchmark, read the failure traces, tweak the prompt, add a tool, rerun. Repeat this a few dozen times and you might move the needle. It’s grunt work dressed up in Python files. AutoAgent, built by Kevin Gu at thirdlayer.inc, proposes a direct alternative: don’t do that work yourself. Let an AI do it. ...

MolmoWeb is Ai2’s open-source browser agent — 8B parameters, Apache 2.0, no API key required. It scores 78.2% on WebVoyager and beats GPT-4o-based agents on multiple benchmarks. Here’s how to get it running locally. System requirements: GPU with at least 16GB VRAM (for 8B model) or 8GB VRAM (for 4B model) Ubuntu 20.04+ or macOS 12+ (Linux recommended for GPU support) Python 3.10+ Chrome or Chromium browser installed Step 1: Clone the Repository git clone https://github.com/allenai/molmoweb.git cd molmoweb Step 2: Create a Virtual Environment and Install Dependencies python3 -m venv molmoweb-env source molmoweb-env/bin/activate pip install -r requirements.txt The requirements include PyTorch, the Transformers library, Playwright for browser control, and Pillow for screenshot processing. The full install typically takes 3–5 minutes on a good connection. ...

The Allen Institute for AI (Ai2) just dropped something the open-source AI community has been waiting for: a fully open, genuinely capable web browser agent that can go head-to-head with GPT-4o-based systems — at 8 billion parameters. It’s called MolmoWeb, and it’s available right now on Hugging Face under Apache 2.0. What MolmoWeb Actually Does MolmoWeb is a multimodal web agent. You give it a natural-language instruction, and it autonomously controls a real web browser: clicking, typing, scrolling, navigating, filling forms. It understands the web visually — through screenshots — rather than through structured DOM parsing. ...

When Anthropic announced on April 4 that Claude Pro and Max subscribers could no longer use their flat-rate plans through third-party agent frameworks, the developer community felt it immediately. More than 135,000 OpenClaw instances were running when the restriction took effect. Now the creator of OpenClaw — who joined OpenAI in February — has gone public with a sharp response, calling the decision a “betrayal of open-source developers.” What Anthropic Actually Did The policy change is straightforward: Claude’s subscription tiers were designed around conversational use. A human opens a chat window, types a query, reads a response. Agentic frameworks operate differently — a single OpenClaw instance running autonomously through a day can consume the equivalent of $1,000 to $5,000 in API costs. ...

The governance infrastructure for autonomous AI agents has lagged badly behind the deployment infrastructure. Frameworks like LangChain, AutoGen, CrewAI, and Azure AI Foundry made it remarkably easy to ship agents that book travel, execute financial transactions, write and run code, and manage cloud infrastructure — all without human sign-off at each step. The guardrails came after, bolted on, or not at all. Microsoft just dropped what might be the most comprehensive attempt to fix that: the Agent Governance Toolkit, open-sourced and available now across Python, TypeScript, Rust, Go, and .NET. ...

Google DeepMind has released Gemma 4, and it’s arguably the most consequential open model drop of the year so far. Not because it’s the most powerful model on any benchmark — it isn’t — but because of what it represents: a fully open-source, Apache 2.0 licensed, agent-ready model family that runs on hardware you already own, including your smartphone. For developers who’ve been waiting for a truly open, production-grade model built for agentic workflows, Gemma 4 is the answer. ...

The most expensive part of your AI agent stack might not be what you think. While developers obsess over model selection and prompt engineering, retrieval is quietly eating your latency budget and your inference bill — and most production RAG pipelines are using general-purpose LLMs for a specialized task they weren’t built for. Chroma’s new Context-1 model is a direct challenge to that pattern. It’s a 20-billion-parameter open-source retrieval model that outperforms GPT-5 on HotpotQA and FRAMES benchmarks while running 10 times faster and costing 25 times less per query. Released on HuggingFace under an open license, it’s purpose-built for one thing: getting the right information out of large corpora for RAG pipelines and agent memory workflows. ...

When Anthropic’s Claude Code source code leaked, the developer community did what it always does: forked it, rewrote it, and published it faster than any legal team could react. Claw Code — a clean-room Python and Rust rewrite of Claude Code’s architecture built by developer Sigrid Jin — has accumulated 72,000 GitHub stars and 72,600 forks since its release, making it one of the fastest-growing open-source repositories in AI tooling history. The first 30,000 stars arrived within hours of publication. ...