Khoj: self-hostable AI second brain with agent and deep research capabilities
Khoj is an open-source, self-hostable AI assistant that supports retrieval from web and local documents, custom agent building, scheduled automations, and deep research workflows. It is model-agnostic, supporting GPT, Claude, Gemini, Llama, Qwen, and Mistral backends. The project has accumulated nearly 35,000 GitHub stars, with modest daily momentum (+53).
Related guides (2)
Related events (8)
Microsoft Build: Seven in-house AI models, GitHub Copilot desktop agent manager, and Web IQ search API for agents
Microsoft announced seven new AI models trained from scratch (not distilled from OpenAI), including the flagship MAI-Thinking-1 reasoning model and MAI-Transcribe-1.5, plus a 'Frontier Tuning' reinforcement learning approach for enterprise workflow training. GitHub released a desktop Copilot app designed to manage multiple parallel AI agents with isolated git worktrees and bidirectional canvases. Microsoft also launched Web IQ, an agent-native Bing-powered grounding API already powering search in Copilot and ChatGPT, running 2.5x faster than alternatives with lower token costs. The roundup also covers Nous Research's Hermes Desktop cross-platform agent app, Alibaba's Qwen3.7-Plus multimodal model, and OpenAI's role-specific Codex plugins.
OpenAI Introduces Deep Research Agent
OpenAI has launched 'deep research,' an agentic capability that uses reasoning to synthesize large volumes of online information and complete multi-step research tasks autonomously. The feature is initially available to ChatGPT Pro users, with rollout to Plus and Team tiers to follow. It represents a step toward practical autonomous research agents built on OpenAI's reasoning model infrastructure.
Co-Scientist: A multi-agent AI partner to accelerate research
Google DeepMind has introduced Co-Scientist, a multi-agent AI system built on Gemini designed to serve as a collaborative research partner for scientists. The system aims to accelerate scientific discovery by assisting researchers across the research workflow. The announcement comes from DeepMind's blog, indicating a formal product or capability launch rather than a research preview.
Le Chat Adds Deep Research, Voxtral Voice Mode, Magistral Reasoning, Projects, and Image Editing
Mistral AI has launched a major feature update to Le Chat, its AI assistant product, introducing five new capabilities: a Deep Research agent mode for structured report generation, a voice mode powered by the new Voxtral speech model, multilingual reasoning via the Magistral model, a Projects workspace for organizing conversations, and advanced image editing in partnership with Black Forest Labs. The update positions Le Chat as a more comprehensive research and productivity assistant across text, voice, and image modalities. Voxtral is introduced here as a new voice-input model, and Magistral is highlighted as the underlying reasoning engine. All features are available immediately at chat.mistral.ai with no credit card required.
obsidian-wiki: AI agent framework for building a digital brain via Obsidian using Karpathy's LLM Wiki pattern
A Python framework on GitHub enables AI agents to build and maintain a personal knowledge base through Obsidian, implementing Andrej Karpathy's LLM Wiki pattern. The project has accumulated 2,015 stars with 137 added today, indicating notable community traction. It sits at the intersection of agent memory management and personal knowledge tooling.
Mistral AI Launches Agents API with Built-in Connectors, MCP Tools, and Persistent Memory
Mistral AI has released a dedicated Agents API that extends beyond chat completion by providing built-in connectors for code execution, web search, image generation, and document retrieval, alongside support for Model Context Protocol (MCP) tools. The API features stateful conversation management with branching, streaming output, and multi-agent orchestration capabilities. Benchmark results show substantial web search augmentation gains: Mistral Large jumps from 23% to 75% on SimpleQA, and Mistral Medium from 22% to 82% with search enabled. The release targets enterprise-grade agentic workflows and is accompanied by cookbooks covering GitHub coding assistants, financial analysis, and travel planning use cases.
Mistral AI Launches Major le Chat Update with Web Search, Canvas, Pixtral Large, and Image Generation
Mistral AI has announced a significant expansion of its le Chat assistant with several new capabilities in beta: web search with citations, a Canvas interface for collaborative document and code creation, multimodal document and image understanding powered by the new Pixtral Large model, and image generation via a partnership with Black Forest Labs (Flux Pro). The update also introduces shareable task agents for workflow automation and speculative editing for faster responses. All new features are currently offered on a free tier, positioning le Chat as a direct competitor to ChatGPT, Claude, and Perplexity.
Onyx: Open Source AI Chat Platform with Multi-LLM Support
Onyx is an open-source AI chat platform written in Python that supports multiple LLMs with advanced features. The repository has accumulated 29,665 total stars with modest daily traction (+28 today). It positions itself as an enterprise-ready AI assistant that integrates with various language model backends.