Open source

Mon, July 6Open Source

MaxKB is an open-source enterprise agent platform gaining significant traction on GitHub.

Mon, July 6Tools

manaflow-ai/cmux is an open-source macOS terminal built on Ghostty, featuring vertical tabs and AI coding agent notifications.

Mon, July 6Open Source

Multica is an open-source hosted agent platform that turns coding agents into real team members, supporting task assignment, progress tracking, and skill compounding.

Mon, July 6Tools

OthmanAdi/planning-with-files is a file-based persistent planning tool designed for AI coding agents and long-running agent tasks.

Mon, July 6Tools

A Claude Code skill called blader/humanizer reached 27,579 stars on GitHub, with 826 new stars in 7 days, topping the trending chart.

Mon, July 6Tools

GitHub trending repo garrytan/gstack offers Garry Tan's Claude Code config with 23 tools covering six team roles from CEO to QA.

Mon, July 6Open Source

claude-mem captures all agent actions in a session, compresses them with AI, and injects relevant context into future sessions.

Mon, July 6Tools

CodeGraph is a pre-indexed code knowledge graph that auto-syncs on code changes and supports AI agents like Claude Code, Codex, and Gemini.

Mon, July 6Tools

Open Design is an open-source, local-first desktop alternative to Claude Design, enabling code agents to generate designs and export to HTML/PDF/PPTX/MP4.

Mon, July 6Open Source

The GitHub trending project agentskills/agentskills provides specifications and documentation for Agent Skills, gaining 2262 stars in 7 days.

Mon, July 6Tools

Headroom is an open-source project that compresses tool outputs, logs, files, and RAG chunks before sending them to LLMs, reducing token usage by 60-95% while maintaining answer quality.

Mon, July 6Tools

Open-source project santifer/career-ops is an AI job search system based on Claude Code, featuring 14 skill modes, a Go dashboard, and PDF generation.

Mon, July 6Open Source

calesthio/OpenMontage is the world's first open-source, agent-driven video production system with 12 pipelines, 52 tools, and 500+ agent skills, turning AI coding assistants into a full video production studio.

Mon, July 6Tools

obra/superpowers on GitHub rapidly gains stars, offering a viable agent skill framework and SDLC methodology.

Sun, July 5Model/API

Mistral co-founder Arthur Mensch warns enterprises against relying on closed AI models, stating that AI labs are storing more customer data and may even use it to compete against customers.

Sun, July 5Tools

LlamaIndex releases legal-kb, a reference app enabling AI agents to access Index v2 document knowledge bases via tools like retrieve, find, read, and grep, resembling a file system.

Sun, July 5Research

This article explains how to use open-source models to convert enterprise data from PDFs, scans, and slides into structured JSON for LLMs and agents.

Sun, July 5Tools

Alibaba has reportedly banned employees from using Claude Code, classifying it as high-risk software.

Sat, July 4Model/API

Mistral AI offers partially open-source AI models and has raised substantial funding since its founding in 2023, aiming to put frontier AI in everyone's hands.

Sat, July 4Research

NVIDIA AI introduces ASPIRE, a framework that writes and improves robot control programs, distilling verified fixes into a reusable skill library.

Fri, July 3Model/API

DeepSeek raises API prices during peak hours, signaling a shift from subsidy-driven competition to sustainable pricing in China's AI model market.

Fri, July 3Tools

Reuters reports Alibaba will ban employees from using Anthropic's coding tools.

Fri, July 3Open Source

Interfaze open-sources diffusion-gemma-asr-small, a multilingual ASR model that transcribes via diffusion instead of autoregression.

Fri, July 3Tools

Amazon Bedrock proposes using generative AI and OSINT to detect high-fidelity phishing emails.

Wed, July 1Model/API

NVIDIA released an open-weight diffusion language model built on a frozen autoregressive backbone.

Wed, July 1Tools

Ollama v0.31.1 uses multi-token prediction to significantly accelerate Gemma 4 inference on Apple Silicon.

Tue, June 30Research

Meta AI releases Brain2Qwerty v2, a noninvasive MEG brain-to-text pipeline with 61% word accuracy, open-sourcing training code.

Tue, June 30Tools

NVIDIA open-sources BioNeMo Agent Toolkit to convert biomolecular models into callable skills for AI agents, boosting task completion from 57.1% to 100% in tests.

Tue, June 30Open Source

DeepReinforce releases its first open-source model, Ornith-1.0, based on Gemma 4 and Qwen 3.5, achieving state-of-the-art results across coding benchmarks.

Mon, June 29Open Source

EverMind open-sourced EverOS, a local-first memory runtime that stores AI agent memory as plain Markdown, indexed via SQLite and LanceDB, with hybrid BM25+vector retrieval, multimodal ingestion, and self-evolving skills.

Sun, June 28Model/API

Liquid AI releases LFM2.5-230M, supporting llama.cpp, MLX, vLLM, SGLang, and ONNX, achieving 213 tok/s on Galaxy S25 Ultra.

Sat, June 27Open Source

Meta released Astryx, an open-source React design system built on StyleX, integrating CLI and MCP server for both human engineers and AI agents.

Sat, June 27Tools

A tutorial on streaming the NVIDIA Open-SWE-Traces dataset from Hugging Face in Google Colab to efficiently process agentic software engineering traces and generate a subset for fine-tuning.

Fri, June 26Open Source

The Linux Foundation and ~20 tech companies, AI labs, and banks launch Akrites to fix vulnerabilities in critical open source software before AI tools can exploit them.

Fri, June 26Model/API

Italian startup Domyn plans to release an open-source frontier AI model within a year.

Fri, June 26Open Source

DeepReinforce releases Ornith-1.0, an open-source coding model family based on Gemma 4 and Qwen 3.5, featuring self-learned RL scaffolds, with the 397B flagship scoring 82.4 on SWE-Bench Verified.

Fri, June 26Agent

AWS unveils open-source Chaplin, a Bedrock-powered AI agent using MCP for self-service health event analysis.

Thu, June 25Tools

Mistral releases OCR 4, transforming document extraction into a comprehensive enterprise AI solution.

Wed, June 24Model/API

Mistral AI released OCR 4 on June 23, 2026, shifting from text extraction to structured document output, supporting 170 languages and self-hosted container deployment.

Wed, June 24Model/API

Datalab releases lift, a 9B open-weight vision model that converts PDFs and images into schema-compliant JSON.