A developer released Perspica, a semantic diff tool for reviewing code, on Hacker News' Show HN. Perspica uses an LLM run to produce semantic groupings of code changes and why they were made, and can …
A developer built a transpiler that converts numerical Python, NumPy, pandas, and partial SciPy code into Fortran using Codex and Claude Code, with some translations running 10-100 times faster and a …
Halv cut recorded model cost by 57.1% versus vanilla Codex across 14 repository tasks, spending $144.67 against $337.50 while both arms passed 25 of 42 runs, according to Halv's own interim benchmark …
AlphaXiv released OpenResearch, a local-first workspace that turns coding agents including Claude Code, Codex, OpenCode, Cursor, and Google Antigravity into research agents that can review literature,…
Magnitude, a Y Combinator S25 company, launched an open source inference engine for AI agents that compiles and tunes its kernels on the user's own device, claiming up to 2x faster performance than ll…
Yolanda and Spencer released a free CLI token compression tool for Codex that cuts input tokens by 29.6% and saves up to 30% on costs, after they burned $700/day per person on API usage. The tool uses…
Developer Vincent Schumacher released explainroo, a free, MIT-licensed open-source framework that lets Claude Code and other AI coding agents such as Codex, Pi and OpenCode produce animated explainer …
Weave released Weave Router 2.0, an open-source model router for coding agents that matches GPT-6 Astra's pass rates on Terminal Bench 4.0 and SWE Atlas while costing 52% and 54% as much and running 2…
TypeSafe released jev-judge-mcp, a Model Context Protocol server that gives coding agents eleven judgment tools backed by its Jev model, returning probabilities in a median 464.6 ms round trip at abou…
A developer built Paveo, a policy checkpoint that intercepts and blocks unsafe tool calls before an AI agent executes them, and replayed two months of their own Claude Code session logs to test it. Ac…
Stack Overflow announced the general availability of Stack Internal on September 30, opening the knowledge-curation platform to anyone via a free Starter workspace at stackinternal.com. The Starter ti…
Moonshot AI's Kimi K3 is now available in OpenAI's enterprise Codex channel through US inference provider Baseten, letting enterprise customers count use of the Chinese model against their existing Op…
A developer who runs multiple AI coding agents audited their rules setup and found that a hand-written "constitution" of agent rules was never actually loaded by any agent, that the rules folder was n…
A developer has released Brand Machines, an open-source agent skill that reviews whether a product's stated brand principles match its actual code behavior, using a worked example of a fictional subsc…
OpenAI rolled out Dots to Pro users in various markets excluding the European Economic Area, Switzerland, and the UK, with availability also for Business Premium users across all supported ChatGPT reg…
OpenAI released GPT-6.1 Sol on September 29, 2026, an upgrade to GPT-6 Sol that the company says nearly matches GPT-6 Astra on coding, computer use and office work at one fifth of Astra's token prices…
A September 29, 2026 arXiv paper introduces agentic meta-reasoning, an inference-time harness that makes an agent's control choices an explicit structured reasoning process, with a controller consolid…
OpenAI announced several new agent capabilities at DevDay 2026, including always-on "Dots" agents, cloud-based Codex, the GPT-6.1 Sol model, and computer use in its Agents API. A developer outlined a …
OpenAI released GPT-6.1 Sol on Tuesday at $2 per million input tokens and $10 per million output tokens, matching Anthropic's Sonnet 5.5 list price, and independent benchmarking firm Artificial Analys…
OpenAI released GPT-6.1 Sol, an upgrade it says delivers near-GPT-6 Astra performance on agentic coding, computer use and professional workflows at one-fifth of Astra's standard token prices, with API…