OPEN SOURCE

On August 5 Cloudflare open sourced Cloudflare OS, the agent workspace it has run internally since May: capability-based Gatekeepers instead of ambient MCP access, apps as private per-user instances, and approvals that simulate outcomes so agents never stall. A concrete blueprint for the company-wide agent platform.

Liquid AI shipped LFM2.5-2.6B on August 4, 2026: a 2.6B open-weight model trained for agentic work inside real harnesses, decoding at 220 tokens/s on an M5 Max and 113 tokens/s on a Ryzen CPU. Here is how it was trained, what the benchmarks say, and how to run it.

Prime Intellect open-sourced Prime Agent on August 5, 2026. It gives the model exactly one tool - a persistent IPython kernel - and lets the harness rewrite its own prompts, skills, memory, and sub-agents mid-run. Here is how it works, what the benchmarks actually show, a full provider and model guide, and an honest comparison to Claude Code, Codex, OpenCode, OpenClaw, Hermes, and Pi.

Shieldstral is a 3B-parameter Apache 2.0 multimodal safety classifier that takes your moderation policy as a plain-language question at inference time, scores content 0-1 in a single forward pass, and runs on one 16GB GPU. It beats 12B-20B guard models on text safety and sets state of the art on multimodal benchmarks.

Steve Yegge's response to AI-generated pull requests suggests a better maintainer workflow: automate triage, repair good ideas, and keep human taste at the boundary.

A ripgrep musl binary crashing during very-large searches turned out to be a suspected Linux 7.0 kernel race - a thread's own store vanishing mid-function. The reporter's instrumentation pinned it, and a kernel-hardening maintainer posted a one-line fix candidate for testing.

An analysis from the Earendil team behind the Pi harness documents how OpenAI, Anthropic, and Google now return provider-sealed state instead of portable transcripts - encrypted reasoning blobs, opaque compaction, hidden subagent messages. The five tests and seven rules for session portability, and why session lock-in matters more than model lock-in.

A new 106-issue benchmark across 49 repositories finds frontier coding agents rarely retrieve AI contribution rules on their own - and never refuse to contribute in AI-banned repositories, no matter the prompt. Disclosure and verification can be fixed; bans cannot.

DeepSeek shipped the official V4 Flash release on July 31, 2026. The re-post-trained 0731 build beats V4-Pro-Preview on agent benchmarks at $0.14/$0.28 per million tokens. Here is what changed and how to run it through OpenCode today.

GitHub open-sourced casefold, a Rust crate that folds the case of every byte Blackbird indexes at memory bandwidth. The counterintuitive trick: delete the early-exit, kill the branches, and fold Unicode as byte arithmetic.

Inkling-Small is a 276B-parameter MoE with 12B active per token, Apache 2.0, and open weights. It beats the 975B Inkling on SWEBench Verified (80.2), HLE (31.6), and tool use at a quarter of the size and a third of the output price.

MiniMax launched H3, an omni-modal generation model that takes text, image, video, and audio input and outputs 2K video with native stereo sound at 0.80 CNY per second. Open weights are promised in the coming days.

A companion guide to the Buzz video: Block's open-source Nostr relay workspace where humans and AI agents share the same rooms, with agent-first CLI, git integration, and workflows. Here is what it does and where it fits in the agentic dev stack.

Mitchell Hashimoto launched Superlogical, a company building a terminal multiplexer for all work: local dev, remote access, and agents. HN reaction, analysis.

Block open-sourced Buzz, a team workspace where agents are cryptographic identities instead of bot tokens. Every message is a signed Nostr event, the relay is yours to run, and the CLI is JSON in, JSON out.

TurboFieldfare is a custom Swift and Metal inference engine that runs Google's 26B-parameter Gemma 4 MoE model in roughly 2 GB of RAM on any Apple Silicon Mac, including 8 GB base models.

PGSimCity is an explorable 3D city that models PostgreSQL internals - shared buffers, WAL, autovacuum, checkpoints, and replication. Built with three.js and TypeScript, it hit #1 on HN with 682 points.

Debian is voting on four proposals to regulate LLM-generated contributions - from an outright ban to full acceptance. The HN discussion reveals the fault lines in open source's biggest AI policy debate yet.

Ruff v0.16.0 ships 413 default rules (up from 59), Markdown code-block formatting, and a new ruff: ignore system. Here is what changed, what HN is saying, and why zero-config linting matters more with AI coding agents.

A technical deep dive into AM halftoning with ImageMagick hit the HN front page at 195 points. We break down the technique, the HN debate on dithering vs halftoning, and why this matters for developers.