Skip to content

#GitHub

0 today

May 22Friday

AI HOT (Curated Pool)

v2.1.147 Release Update

Claude Code v2.1.147 adds a Workflow tool, disabled by default, for deterministic multi-agent orchestration, and renames /simplify to /code-review with code-correctness reporting and GitHub PR inline-comment generation.

Why it matters: Claude Code v2.1.147 adds a Workflow tool, off by default, for deterministic multi-agent orchestration, and renames /simplify to /code-review with support for generating inline PR comments.

May 20Wednesday

AI HOT (Curated Pool)

Microsoft reportedly warns internally that GitHub faces existential risk as AI coding tools reduce hosting need

Microsoft internally warned that GitHub faces an existential risk from AI coding assistants such as Cursor and Claude Code, and told some teams to stop using Claude Code by the end of June 2026 and move to GitHub Copilot CLI.

Why it matters: Microsoft's internal view is that AI coding assistants like Cursor and Claude Code are changing how developers commit code, hitting GitHub's core hosting business.

AI HOT (Curated Pool)

Smarter Google AI Edge Gallery: MCP Integration, Notifications, and Session Continuity

Google AI Edge Gallery adds experimental MCP support on Android, letting Gemma 4 coordinate external data sources including Google Workspace and Google Maps; the update also adds scheduled notifications and persistent chat history for faster restoration of long-session context.

Why it matters: Google is testing a way for on-device models to call outside tools, which is the part of phone AI that usually stays closed.

May 19Tuesday

AI HOT (Curated Pool)

Take your local GitHub sessions anywhere

GitHub launched remote control sessions for Copilot, letting users start tasks in VS Code or the command line and continue them through github.com or GitHub Mobile.

Why it matters: GitHub added remote session control to Copilot, so a bug fix or refactor started locally can be tracked and continued from phone or web, giving cross-device AI assistant sessions a concrete entry point.

May 15Friday

AI HOT (Curated Pool)

X open-sources the “For You” feed recommendation algorithm

X open-sourced the For You recommendation pipeline on GitHub, using a Grok-based Phoenix Transformer to score candidate posts and predict engagement probabilities such as likes, replies, and reposts.

Why it matters: X published the recommendation pipeline behind its For You feed on GitHub, including code, pretrained models and content-understanding services, with a Grok-based Phoenix model scoring candidate posts.

AI HOT (Curated Pool)

Feishu Open-Source CLI Tool Gets 10,000 Stars in 45 Days with Visible AI Operations

Feishu’s open-source lark-cli gained over 10,000 GitHub stars in 45 days, letting AI create groups and documents through the command line with each operation previewable and reviewable.

Why it matters: Feishu open-sourced the lark-cli command-line tool, which passed 10,000 GitHub stars in 45 days and shows each AI action before confirming it, unlike cloud MCP tools that run as a black box.

May 14Thursday

AI HOT (Curated Pool)

WeChat Group Chat Summary Skill Added, Depends on wx-cli Configuration

baoyu-skills added a WeChat group chat summary Skill that depends on wx-cli for data reading; the post provides two GitHub links and says Claude Code plus Claude Opus 4.6 gives the best results.

Why it matters: baoyu-skills added a WeChat group chat summary Skill that needs wx-cli installed first to read chat data, and the author found Claude Code with Claude Opus 4.6 worked best.

May 13Wednesday

AI HOT (Curated Pool)

GitHub Copilot Individual Plans Add Flex Allotments and a New Max Plan

GitHub will update Copilot individual plans on June 1 by adding flex allotments to Pro and Pro+ and introducing a new Max plan; the post does not disclose pricing, quota limits, or the exact allocation rules in the provided snippet.

Why it matters: GitHub added flexible quotas to Copilot Pro and Pro+ for access to higher-tier models and features, plus a new higher-priced Max plan, giving individual users one more tier to pick from.

May 12Tuesday

AI HOT (Curated Pool)

Dungeons & Desktops: Building a Procedurally Generated Roguelike with GitHub Copilot CLI

A GitHub employee used GitHub Copilot CLI to build an extension that parses any codebase into one Roguelike-style dungeon layout, with procedural level generation used as the core mechanism for a creative coding and game prototyping demo.

Why it matters: A GitHub engineer turns any repo into a Roguelike dungeon map with Copilot CLI, where code structure generates the rooms and corridors.

May 11Monday

AI HOT (Curated Pool)

Anthropic open-sources full-stack financial AI templates

Anthropic open-sourced a financial services AI template library on GitHub, including 10 end-to-end agents, 7 vertical industry plugins, and MCP connectors for 11 financial data providers, with deployment paths from personal plugins to enterprise APIs and integrations for Microsoft 365 and private cloud.

Why it matters: Anthropic open-sourced a full-stack finance AI template on GitHub with 10 agents, 7 plugins and connectors to 11 data vendors, giving finance AI projects a reusable engineering starting point.

AI HOT (Curated Pool)

Codex autonomously completes a security audit and earns a bounty

A user instructed Codex to earn $5; Codex spent about 22 hours finding an open-source security audit bounty, submitting a valid PR, communicating with maintainers, passing GitHub verification, and ultimately receiving a $16.88 payment.

Why it matters: A Codex agent ran a full security-audit bounty loop on its own for about 22 hours, from finding the bug to getting its fix merged for $16.88.

May 8Friday

AI HOT (Curated Pool)

OpenAI launches official openai-cli for terminal API calls

OpenAI open-sourced openai-cli for direct API calls from the terminal. The Apache 2.0 tool installs via Homebrew or Go and covers Responses API, structured output, image editing, transcription, and key config. The key detail is Agent workflows using cloud tools like web search and code interpreter.

Why it matters: OpenAI open-sourced openai-cli, letting developers call the API from the terminal and chain cloud tools like web search and the code interpreter, skipping the SDK code they used to write.

AI HOT (Curated Pool)

Agent Pull Requests Are Everywhere: How to Review Them

GitHub published a guide for reviewing pull requests generated by AI agents. The snippet lists 3 focus areas: code changes, logic or security bugs, and pre-merge technical debt. The key issue is a review process before automated commits reach production.

Why it matters: A GitHub blog post lays out a three-step method for reviewing AI agent pull requests, from reading the diff to hunting logic and security bugs to clearing tech debt before merge.

AI HOT (Curated Pool)

DeepSeek 4: Flash Local Inference Engine for Metal

DeepSeek 4 Flash is open-sourced on GitHub for offline inference on Apple Silicon Macs. The post says it uses Metal Performance Shaders to reduce latency and memory use, but discloses no benchmark numbers. The key item is the Metal local inference stack, not another model wrapper.

Why it matters: antirez, the creator of Redis, shipped ds4 to run DeepSeek 4 Flash locally on a Mac, calling Apple's Metal Performance Shaders directly to cut latency and memory use.

May 5Tuesday

Xinzhiyuan · WeChat

$1 for 10 Stars: ICSE Paper Exposes Fake GitHub Star Market

CMU researchers scanned GitHub events from July 2019 to Dec. 2024, flagging 6 million suspected fake stars. StarScout ran on about 20 TiB and found 18,617 repositories and 301,000 accounts. The supply-chain risk is concrete: GitHub deleted 90.42% of flagged repos, and about 30% of live samples were spam, phishing, or malware.

Why it matters: A CMU team scanned five years of GitHub logs and found roughly 6 million suspected fake stars, showing how cheap repo credibility has become.

May 4Monday

QbitAI · WeChat

DeepSeek-TUI, a “DeepSeek Claude Code,” reaches 2.3k GitHub stars

DeepSeek-TUI reached 2.3k GitHub stars; the Rust project is MIT-licensed. It targets DeepSeek V4 with a 1M-token context, RLM up to 16 V4 Flash subtasks, MCP, Shell, Git, and three control modes. Watch cache misses: uncached tokens cost 10x cached tokens.

Why it matters: DeepSeek-TUI is a Rust terminal coding assistant wired to DeepSeek V4 with 1M-token context, MIT-licensed, for developers studying command-line AI coding tools.

Apr 30Thursday

Xinzhiyuan · WeChat

AI Raw Proofs Pile Up on GitHub as Terence Tao Says Solving Alone Is Not Enough

Terence Tao says math is shifting from proof scarcity to proof abundance, with 20-plus AI solutions pending assessment on an Erdős problems GitHub page. The post says GPT-5.4 Pro generated an Erdős #1196 approach in 80 minutes, and Tao verified the core within 24 hours. The key issue is verification and digestion workflow, not raw proof count.

Why it matters: Terence Tao says math's bottleneck has flipped from too few solutions to too many; one Erdős problem page has 20-plus AI-generated solutions waiting for review, leaving the field to work out verification and digestion.

Apr 28Tuesday

Hacker News front page

GitHub Copilot code review will start consuming GitHub Actions minutes

GitHub will make Copilot code reviews consume GitHub Actions minutes starting June 1, 2026. Private-repo reviews use plan entitlements, with overages billed at standard Actions rates; public repos stay free. The change covers Copilot Pro, Pro+, Business, and Enterprise, including direct org billing for unlicensed users.

Why it matters: GitHub told users Copilot code review will draw on Actions minutes from June 1, 2026, so the same task will consume both AI credits and CI time.

X · @dotey

GitHub Copilot switches to usage-based billing on June 1

GitHub Copilot will switch to AI Credits billing on June 1 while keeping subscription prices unchanged. Credits count input, output, and cached tokens; Pro includes $10 monthly credits and Pro+ includes $39. Watch Copilot Agent long-task costs.

Why it matters: From June 1 GitHub Copilot swaps premium requests for AI credits charged by token use, with subscription prices unchanged at $10 for Pro and $39 for Pro+, so heavy users face unpredictable bills.

Hacker News front page

GitHub Copilot is moving to usage-based billing

GitHub said on 2026-04-27 that GitHub Copilot will move to usage-based billing. The captured post only shows the title, time, and navigation. It does not disclose the launch date, usage metric, prices, or overage rules.

Why it matters: GitHub is dropping Copilot's flat monthly fee for usage-based billing, though the metering metric and unit price are not yet disclosed, so teams should watch how their usage gets counted.

Apr 25Saturday

Hacker News front page

Open-source memory layer Stash lets any AI agent do what Claude.ai and ChatGPT memory can do

Stash released an open-source persistent memory layer for AI agents, exposing 28 MCP tools and a 6-stage pipeline for long-term memory. The page says it uses PostgreSQL plus pgvector and hierarchical namespaces to separate user, project, and self memory. The real point is a portable memory layer, not the headline claim about matching ChatGPT or Claude.ai.

Why it matters: Stash ships an open-source memory layer on PostgreSQL and pgvector, with 28 MCP tools and a 6-step pipeline that adds fact extraction, a knowledge graph and contradiction checks beyond plain RAG.

Apr 23Thursday

Hacker News front page

Coding Models Are Doing Too Much

The author programmatically corrupts 400 BigCodeBench problems with single-point bugs to test whether coding models over-edit code during fixes. The post defines the minimal fix as exactly reversing the corruption and measures excess changes with token-level Python Levenshtein distance. The provided body does not disclose final results, model rankings, or training gains.

Why it matters: The author plants single-point bugs in 400 BigCodeBench tasks and uses token-level edit distance to measure how much models over-rewrite when fixing bugs, then tries to train them to make minimal edits.

Apr 21Tuesday

QbitAI · WeChat

GitHub Stars are openly sold for RMB 0.5 each, with AI projects hit hardest by fake stars

Carnegie Mellon University reports about 6 million suspected fake GitHub Stars from 2019 to 2024, spanning 18,617 repositories and over 300,000 accounts. Its StarScout tool flags bot accounts and synchronized starring, with 81% accuracy; 78 heavily inflated projects reached Trending. The key point for AI practitioners: the post says AI/LLM projects rank first in fake-star volume among non-malicious repos, and the boost lasts under two months.

Why it matters: Carnegie Mellon researchers identified about 6 million suspected fake stars across more than 18,000 GitHub repos, including 78 heavily inflated projects that reached the Trending page.

Hacker News front page

CrabTrap: An LLM-as-a-judge HTTP proxy to secure agents in production

Brex open-sourced CrabTrap, an HTTP proxy that intercepts every agent request and allows or blocks it against a policy in real time. The page shows a dual path of static rules plus an LLM judge, and logs whether each decision came from rule matching or model judgment; the post does not disclose the model, latency overhead, or error rates.

Why it matters: Brex open-sourced CrabTrap, an HTTP proxy that sits between agents and external services, matching requests against static rules first and sending the rest to an LLM judge.

X · @dotey

GitHub paused new sign-ups for Copilot Pro, Pro+, and Student on April 20

GitHub paused new sign-ups for Copilot Pro, Pro+, and Student on April 20, leaving only Copilot Free open to new users. The post says Pro+ now has more than 5x Pro usage, Claude Opus 4.7 is limited to Pro+, and users can request cancellation with a full April refund from Apr 20 to May 20. What matters is the price stayed fixed while access, quotas, and model tiers tightened first.

Why it matters: GitHub paused new signups for Copilot Pro, Pro+ and the student tier, pulled Claude Opus from the Pro plan, and raised Pro+ quotas to more than five times Pro.

Apr 16Thursday

Latent Space

[AINews] RIP Pull Requests (2005-2026)

GitHub is, for the first time 21 years after pull requests emerged, letting open-source repos disable PRs; the post frames this as a signal that AI coding workflows are changing collaboration. It gives a 2005-to-2026 timeline and cites agent stacks from OpenAI and Cloudflare as pressure toward prompt-driven contributions and sandboxed execution; the real question is whether Git-based workflows still fit agent collaboration.

Why it matters: GitHub now lets open source repos turn off Pull Requests entirely, the first such change in 21 years, raising whether Git's human workflow still fits agent-to-agent work.

Apr 15Wednesday

X · @dotey

pi maintainer Mario Zechner sets a new rule: unapproved issues and PRs will be auto-closed immediately

pi maintainer Mario Zechner says any issue or PR submitted without prior approval will be auto-closed, after he started receiving 30 to 50 issues per day and most were AI-agent spam. He will still review closed submissions daily; strong issues can earn an “lgtmi” tag, and strong issue-plus-fix PRs can earn “lgtm,” exempting future submissions from auto-close. The shift to watch is simple: open source projects are raising contribution gates to filter zero-cost AI-generated noise.

Why it matters: pi maintainer Mario Zechner gets 30 to 50 mostly AI-generated issues a day, so unapproved submissions are auto-closed by a bot and he manually reopens the good ones.

Mar 6Friday

Ruan YiFeng's Weblog

Technology Enthusiast Weekly Issue 387: You Are Ahead

Ruanyifeng says that, out of 8.1 billion people, only 1.38 billion have used AI, or 16%; just 15 to 25 million pay for AI services, or 0.3%. The post adds that only 2 to 5 million people have used AI to create their own coding projects, or 0.04%. The real signal is the adoption gap, not the idea that everyone already uses AI.

Why it matters: Ruan Yifeng breaks down global AI adoption with three numbers, from 16% who have used it to 0.04% using it for programming, sketching where people who follow AI news actually sit.

Feb 4Wednesday

TheValley101 (硅谷101)

E224 | Why Clawdbot became the first breakout product of 2026 amid the Mac mini rush | Moltbot | MoltBook | OpenClaw

The podcast says Clawdbot passed 100k GitHub stars within days and reached 146k on Feb. 2, while being renamed to Moltbot and then OpenClaw within a week. It attributes the traction to a stack of Claude, long-term memory, IM-based messaging, and proactive heartbeat workflows; the title mentions a Mac mini rush, but the post does not disclose sales figures. The real signal is the interaction layer rather than a new model release: this is industry commentary and user anecdotes, not an official spec sheet.

Why it matters: This podcast breaks down Clawdbot's surge from user, software and hardware angles, then tracks the reversals that followed: the rename, the lawsuit, exposed security holes and servers going down.

Sep 25, 2025Thursday

OpenAI News

More ways to work with your team and tools in ChatGPT

OpenAI rolled out shared projects for ChatGPT Business on September 25, 2025, and made them available for Enterprise and Edu plans. Shared projects support email or link invites, two access levels, and private project memory; Enterprise and Edu have them off by default under admin control. OpenAI also added Gmail, Google Calendar, Outlook, Teams, SharePoint, GitHub, Dropbox, and Box connectors, and said ChatGPT can now choose connectors automatically per prompt.

Why it matters: Shared projects give paid Business, Enterprise and Edu teams one space for files and instructions, so members reuse the same context instead of re-explaining it.

Sep 15, 2025Monday

OpenAI News

Introducing upgrades to Codex

OpenAI released GPT-5-Codex and made it the default model for Codex cloud tasks and code review; in testing, it worked independently for more than 7 hours on complex tasks. OpenAI says it used 93.7% fewer tokens than GPT-5 on the lowest 10% of employee turns, while spending 2x longer reasoning, editing, and testing on the highest 10%. The key point is one model now spans interactive coding and long-running agentic execution; pricing and full availability details are not fully disclosed in the provided body.

Why it matters: OpenAI makes GPT-5-Codex the default model for Codex cloud tasks and code review, built for both interactive coding and long autonomous runs, with tests lasting over 7 hours.

OpenAI News

Addendum to GPT-5 system card: GPT-5-Codex

OpenAI published a GPT-5-Codex system card addendum on September 15, 2025, stating the model is optimized for agentic coding in Codex and is available in terminal, IDE, web, GitHub, and the ChatGPT mobile app. The post says it uses reinforcement learning on real-world coding tasks, plus safety training for harmful tasks and prompt injection, with sandboxing and configurable network access. Benchmark scores, pricing, and context window are not disclosed.

Why it matters: OpenAI adds a system card addendum for GPT-5-Codex, covering the reinforcement learning used for Codex agentic coding and its safety measures, and noting it runs in the terminal, IDE, web, GitHub and ChatGPT mobile.

May 16, 2025Friday

OpenAI News

Addendum to OpenAI o3 and o4-mini system card: Codex

OpenAI published a May 16, 2025 addendum to the o3 and o4-mini system card, stating that Codex is a cloud coding agent powered by codex-1, an o3 variant tuned for software engineering. Each agent runs in an isolated cloud container preloaded with the user's code and environment, then loses internet access while it reads or edits files and runs tests, linters, and type checkers. The practical detail is the audit trail: Codex cites terminal logs and files, and its output can be exported as a GitHub PR or local diff.

Why it matters: The addendum states codex-1 is an o3 variant trained with reinforcement learning to run tests until they pass, exposing how the cloud coding agent works.

OpenAI News

Introducing Codex

OpenAI released the Codex research preview on May 16, 2025, a cloud software engineering agent powered by codex-1 that can handle multiple coding tasks in parallel. It runs each task in an isolated sandbox, can read and edit repos, execute tests and commands, and usually finishes in 1 to 30 minutes with terminal logs and test outputs as evidence. It launched for ChatGPT Pro, Business, and Enterprise users, then expanded to Plus on June 3; the post excerpt does not fully disclose pricing or complete limitations.

Why it matters: Codex dispatches coding tasks in parallel from the ChatGPT sidebar, showing the shift from code completion to task-level agent work.

Aug 13, 2024Tuesday

OpenAI News

Introducing SWE-bench Verified

OpenAI released SWE-bench Verified, a human-validated subset built with the benchmark’s authors to assess real software issue resolution more reliably. The post names 3 failure modes in SWE-bench: overly narrow tests, underspecified issue statements, and unreliable environment setup; as of Aug. 5, 2024, top agents scored about 20% on SWE-bench and 43% on SWE-bench Lite. The key point is that the original benchmark can systematically underestimate coding-agent ability.

Why it matters: OpenAI and the original SWE-bench authors built a human-verified subset, arguing the original systematically underestimates real coding ability due to rigid unit tests, vague descriptions and environment issues.