#open-source

Microsoft Research's Flint 1.0 lets agents describe chart interactions as semantic events and update operators. What it compiles, where it stops, when it helps.

A census of 21 training-cost figures labs published themselves, 2022 to 2026. Six give a dollar amount, none is audited, and each leaves something out.

Xiaomi says six days of RL on MiMo-V2.6 cost about $850,000 for Flash and $2.62 million for Pro. What the figure covers, what it leaves out, and the prices.

16 models in the open-model conversation, checked against the licence file, OSI's list and what else was released: weights, data, recipes, evaluation harness.

OpenAI committed $1 billion in subsidised Daybreak access over six months. What it is, which organisations are prioritised, and what remains unpublished.

curl’s maintainer posted that Mythos and Codex Security had nothing left to find. Days later AISLE filed 29 reports; six became Low CVEs in curl 8.22.0.

OpenClaw 2.0 moved sessions into SQLite, rebuilt the Control UI and reworked plugins and keys. Its headline startup number is a mocked-Gateway lab result.

Credentio validates C2PA Content Credentials on-device, and Google says it runs in nearly 40 of its own products. What a credential proves, and what it cannot.

DeepSeek open-sourced its dsh agent harness under MIT: a developer preview at 0.1.0-rc.5, four runtime modes, and every part of the product a plugin.

Both terminal harnesses ship bash sandboxing off by default. The differences that hold up are openness, model freedom and what each vendor publishes.

SpaceXAI open-sourced Grok Build's Rust harness under Apache 2.0 days after a privacy scandal. Why a public repo is not the same as a security audit.

Vercel launched eve, an Apache-2.0 TypeScript agent framework where every agent is a directory. What it is, how it works, and how it compares.

Gemini CLI stops serving Pro, Ultra, and free users on June 18, 2026. The 45-minute migration to Antigravity CLI, the silent failures, and the quota regression.

Hermes Agent hit 180K GitHub stars on a self-improving GEPA loop. A complete 2026 guide to the open-source desktop app: install, memory, skills and sessions.

Hands-on deep dive into Continue.dev — the open-source AI coding assistant, model routing, context providers, slash commands, IDE integrations.

n8n now offers 70+ AI nodes for building LangChain agent workflows in open-source. Setup guide for autonomous AI automation pipelines without vendor lock-in.

NVIDIA releases Nemotron 3 Super 120B with 60.47% SWE-Bench Verified and 2.2x throughput. Open-source coding model for enterprise AI agent deployments.

Lightricks releases LTX-2.3, a 22B parameter open-source AI video model generating 4K video at 50 FPS with synchronized audio under Apache 2.0 license.

Alibaba releases OpenSandbox under Apache 2.0. Open-source AI agent execution platform gains 3,845 GitHub stars in 2 days with multi-language SDK support.

Build and publish skills for OpenClaw's ClawHub marketplace with 3,000+ extensions. Developer guide covering architecture, security, and publishing.

Master FLUX.2 Max by Black Forest Labs. Web-grounding, 10 reference images, #2-3 on leaderboards. Complete guide with pricing and creative workflows.

Master the Agentic AI Foundation with MCP, goose, AGENTS.md. Linux Foundation backing from OpenAI, Anthropic, Block. Complete guide.

Historical Kimi K2-0905 release guide refreshed for 2026 context, with agentic coding, MoE architecture, deployment, and newer Kimi caveats.

Historical 2025 comparison of Kimi K2, Qwen 3 Coder, and GLM 4.5 refreshed with April 2026 caveats for newer Chinese and frontier AI model selection.

Use Gemini CLI with current Google free-tier limits, open-source caveats, MCP support, auth options, and safe production workflow guidance.