Tencent Cloud released TeamAI (github.com/Tencent/teamai-cli) on October 10, an open-source team AI collaboration tool previously used internally that has since appeared on GitHub Trending. Built on Git, TeamAI stores team skills, working conventions, tool configurations and project knowledge in a repository so they can be reviewed and versioned like code, then synced to each member's agent; the company says it supports 16 agents including WorkBuddy, CodeBuddy, Claude Code, Codex and Cursor. Tencent Cloud says a test spanning 13 engineering tasks found a lower-cost model scored 6.1% higher and used 76% less model-call cost after gaining access to team knowledge, and the tool is integrated into its ClawPro agent management platform.
Developer Paul Hudson (Hacking with Swift) published SwiftUI Pro on GitHub, an agent skill that helps AI coding assistants such as Claude Code, Codex, Gemini and Cursor write more modern, simpler SwiftUI. The skill builds on his existing AGENTS.md work and targets mistakes LLMs actually make — deprecated API usage, VoiceOver/accessibility problems and surprising performance issues — covering navigation, layout, animations and state management. It installs via npx skills add or the Claude Code plugin marketplace and is triggered with /swiftui-pro in Claude Code or $swiftui-pro in Codex; it is MIT-licensed, with sibling skills including SwiftData Pro, Swift Concurrency Pro and Swift Testing Pro.
REA (Reverse Engineer Anything) is an MIT-licensed TypeScript project by developer morluto that puts tools such as Ghidra, Hopper and IDA behind an MCP server so coding agents like Claude Code, Codex, Cursor and Gemini CLI can investigate software without source code. 36Kr reported the repository had about 120,000 GitHub stars by Oct 12, with growth surging after a 4.1.0 release on Oct 7 added mobile-app analysis, though other reports put the count at roughly 50,000–80,000. Documented examples include recovering a DX-Ball sound-panning routine as C code that passed 3,205 original x86 test cases, and tracing Notion's clipboard bridge; the community has since pointed it at Adobe and Google apps plus WeChat, Alipay and Douyin, though 36Kr notes those apps' core logic runs server-side behind packing, obfuscation and risk-control defenses.
A hands-on piece from OSChina uses TypeSafe Jev's three judgment primitives — Choice, Noul and Score — to auto-triage vulnerability reports submitted to a low-code platform, reporting that it screens 8 reports in about one second and that the judgment logic can be wired into Claude Code and Codex. The article also notes Jev is now fully open with no waitlist and a console at console.typesafe.ai, though the earlier free credit for new users has been dropped: sign-up is free but requesting an API key requires binding a payment method.
A Product Hunt listing for AgentDock says it lets users answer Claude Code and Codex from a single inbox inside any terminal. The listing itself is only a one-line pitch and gives no details on features, supported terminals or pricing.
In a blog post, Simon Willison describes using the voice conversation mode in the Codex tab of the ChatGPT desktop app, running against a local dev environment, to add a Newsletters index page to his blog. He says roughly half an hour of voice conversation while cooking produced a Django model and migration, views, templates and four import scripts from the model GPT-6 Astra High; he then switched to typing to rework one import to use an API and landed the PR. He concludes voice plus live visual preview is great for multi-tasking but not yet a daily driver for detailed work.
Zentrola, an AI coding governance platform for engineering teams, released version 1.1.0. It sits between clients such as Codex and Claude Code and enterprise model services, letting developers keep their usual tools while administrators centrally manage model access, credentials, usage and cost. The update adds application access, cost attribution and monthly token quota controls on top of its existing model governance features, allowing applications to call models independently.
TypeSafe founder Diogo Almeida, who previously worked on OpenAI's InstructGPT, told the Latent Space podcast that the AI world before Jev was "a tragedy": strong intelligence engines exist, but the interface for wiring them into real business processes is missing. He describes Jev as a System 1 or "large programmable" model trained with reinforcement learning for calibrated decisions (RLCD), so code can directly consume its choices, scores and probabilities and set thresholds for when to act or hand off to a human. He also criticises RLHF mode dropping for distorting calibration, argues specific value judgments should not be baked into a general model's底层 behaviour, and says he dislikes optimising for public leaderboards, adding that benchmark-use restrictions came from preview terms and will be revised.
BMAD-METHOD (Breakthrough Method for Agile AI Driven Development) is a free, MIT-licensed open-source method for turning an idea or change request into working software inside AI coding tools, keeping decisions explicit and context durable. It installs via the Skills CLI (npx skills add) or through the Claude Code and Codex plugin marketplaces, requiring an AI coding tool that supports skills plus uv for setup, and it scales its planning depth to the size of the change. Optional modules include BMad Builder, a Creative Intelligence Suite, Test Architect, BMad Loop and a Game Dev Studio, usable for greenfield prototypes or established codebases.
Frank Hidalgo, StackAI CTO at Asana, used GPT-6 Astra in Codex to profile and refactor the company's browser agent, producing an optimized workflow on GPT-6.1 Sol that averaged about $0.47 in estimated model cost and roughly four minutes per run across a 144-run study — 76x cheaper and 5x faster than the original production setup on an anonymized 'Model B'. He estimates the work would have taken one to two months by hand but took about a week. The gains came from extending caching to browsing history, raising the history budget to 480,000 characters and batching screenshot removal; Asana says the browser-navigation changes have shipped in StackAI.
A 少数派 AI walkthrough of OpenAI DevDay describes Dots as a personal assistant with its own cloud computer and browser, driven by GPT-6 Astra; it launches with a single "primary dot", rolling out to Pro and Business Premium in eligible markets, with admin-enabled betas for Enterprise, Edu and Healthcare. Space and Pages, replacing Library, give teams shared material and co-editable documents, while the article says GPT-6.1 Sol is an upgrade on GPT-6 Sol that nears Astra on coding, computer-use and professional-work benchmarks at $2 per million input tokens, $0.10 cached input and $10 output (about one-fifth of Astra's standard API price), with Ultrafast running roughly 8x faster in Codex and up to 300 tokens/second, and a $500/month Pro 500 tier offering 25x Plus usage. Developer items include the open-sourced Codex Harness, Codex Cloud, Security Cloud, Agents API, a limited-preview Decisions API, plus Plugins, Sign in with ChatGPT and the enterprise-procurement Marketplace.
In a Latent Space podcast interview, OpenAI's computer-use product and engineering lead Ari Weinstein and API product lead Nikunj Handa discussed the DevDay (Sept 29) launches: Dot, GPT-6.1 Sol, computer use in the Agents API, and the Decisions API. Handa said the Decisions API was inspired by Jev and was not originally planned; the team had a working prototype in about a week, without retraining a model — reusing Luna weights, constraining outputs to structured results and optimizing first-decision latency for fast classification tasks such as support-ticket triage, and pairing with GPT Live. Weinstein said the biggest improvement in computer use over the past year is that agents now debug and retry better, and can act via page structure, accessibility data and Playwright or by writing code rather than only clicking through screenshots.
On Oct 8 OpenAI added an Ultrafast service tier to the Responses API for GPT-6.1 Sol, keeping the same gpt-6.1-sol model ID and switching via service_tier; it is open to all API users but subject to separate rate limits, with global processing and US/EU data residency. OpenAI says it offers near-Astra intelligence at up to 8x the speed of Sol Standard, priced at $12 per million input tokens and $60 per million output tokens — 6x standard and above GPT-6 Astra's standard $10/$50 rates; OpenRouter said the tier is live there too. In ChatGPT, Ultrafast is limited to Codex and ChatGPT Work for the $500 Pro plan and eligible Enterprise and Edu plans. Zhidx and InfoQ reported community pushback, with users complaining that Sol Standard is already slow and the tier amounts to a price increase.
A PyTorch blog post details how NVIDIA Dynamo turns request-level serving into program-aware serving using one session-level identifier, with child sessions carrying a parent_session_id. Dynamo recognizes the session headers that Claude Code, Codex and OpenCode already emit, while other harnesses opt in via X-Dynamo-Session-ID, and plugins exist for Hermes and OpenClaw. The post also covers session-aware routing and admission control (porting a scheduler from the ThunderAgent paper), a shared KV cache indexer, the Session-Prefix Indexer and proposed KvHint interface, plus DYN_REQUEST_TRACE=1 trace capture with AISimulate offline replay and AIPerf live benchmarking.
a16z published an essay arguing AI is turning the CFO from scorekeeper into a builder of the company's "operating system," as easier data access and AI-native finance tools compress deployment from quarters to days and push reporting toward continuous, real-time closes. It cites Anthropic's finance team maintaining 70-plus finance-specific AI skills treated like production code — one of which produces a 90–95% complete monthly financial review in about 30 minutes — and OpenAI CFO Sarah Friar's team building custom GPTs and live dashboards for investor relations and procurement. The piece also highlights a16z portfolio companies including Rillet, Concourse, Lio, Stuut, Sphere, Petual and CFO.ai, and describes a rising "finance engineer" role using Codex or Claude Code, with lean teams targeting roughly 2% of headcount versus the traditional 5%.
Thibault Sottiaux, who leads OpenAI's core products and platform, said ChatGPT Work and Codex have reached a new high of 40 million active users. Peter Gostev, who heads the Arena.ai (LMArena) evaluation platform, projected that if the trend continues the figure would reach roughly 70 million by year-end and about 100 million by the end of March 2027 — a third-party estimate, not OpenAI guidance.
After embedding Codex in its development process, LegalOn Technologies initially gave engineers unlimited access to GPT-5.5 in Fast mode, which pushed up spending. Its AI-powered Development CoE then introduced model-selection guidelines: GPT-6 Luna for everyday implementation, GPT-6.1 Sol for standard design, data analysis and documents, and GPT-6 Astra for complex analysis, architecture and agent orchestration, alongside restricting Fast mode by default and setting monthly budget caps per department, group and individual. OpenAI says the company cut estimated daily costs by roughly 65% versus GPT-5.5 while maintaining development speed, with mature businesses asked for about 20% better cost efficiency and new businesses given generous budgets.
A Chinese-language feature interviews more than ten practitioners from non-tech sectors and profiles five cases: a Foshan pig-farming-supplies owner who used AI to generate leads, move his company to the cloud and rewrite a decade-old software product; a Shanghai Jiao Tong team building AI scheduling and decision systems for manufacturers; a recent graduate who turned month-end reconciliation into an agentic workflow; and a county physics teacher and an equipment-rental owner using AI for interactive courseware and quotes. It reports that Muyuan, described as the world's largest pig producer, built a pig-farming model with Alibaba Cloud that distils veteran vets' disease-diagnosis experience into one-second results deployed across more than 1,000 farms. The article cites CAICT, McKinsey and MIT NANDA survey figures to argue the real obstacles are fragmented data, customer education and cross-department authority rather than the models themselves.
The GitHub project MDX-Tom/gpt-instruct offers Codex jailbreak prompts plus a reproducible evaluation toolchain aimed at improving first-pass execution, process continuity and artifact verification on complex tasks, with runnable rollback. It maintains three lines: the stable gpt-5.6-sol-v45 and two pre-releases, gpt-6-astra-v2-rc1 and gpt-6.1-sol-v1-rc2; the author reports B-tier non-cloud scores of 42/50 cases for Astra and 34/50 for 6.1, with C-tier tests not run for either. The project says it is for AI-safety purposes only, uses Codex's official configuration mechanism, and warns that jailbreak activity carries account risk, recommending throwaway accounts.
Uber has open-sourced ADR (Agentic AI Detection and Response), an enterprise security system for AI agents that is deployed in production at the company. The repository includes ADR Discovery, ADR Sensor, ADR-Bench and ADR Detector, which inventory AI apps, CLI agents, IDE extensions, local model runtimes and MCP servers on endpoints, and capture agent intent, tool use and execution traces from 7+ coding tools including Claude Code, Cursor, Codex, GitHub Copilot CLI, DeepSeek Harness, opencode, Claude Desktop and Gemini CLI. The project says ADR-Bench spans 304 tasks and 134 MCP servers across all 17 agent attack techniques; the ADR Prevention component and the ADR Explorer engine are not part of the open-source release, and an accompanying paper was accepted to MLSys 2026.
manaflow-ai's cmux is an open-source, GPL-licensed macOS terminal that renders via Ghostty's libghostty and is built natively in Swift/AppKit rather than Electron. Its sidebar provides vertical tabs showing git branch, linked PR status and number, working directory, listening ports and latest notification text, and it hooks into agents such as Claude Code and OpenCode through OSC 9/99/777 sequences and a cmux notify CLI, giving a waiting agent a blue pane ring and a lit-up tab. It also adds a scriptable in-app browser ported from agent-browser, workspaces with horizontal and vertical splits, a CLI and socket API for automation, and resume integrations for Claude Code, Codex, Gemini, Cursor CLI and others; it installs via DMG or Homebrew, with separate nightly builds.
Developer Addy Osmani has published agent-skills on GitHub, an open-source pack that encodes senior-engineering workflows, quality gates and best practices as 25 skills (24 lifecycle skills plus a meta-skill) mapped to six phases: DEFINE, PLAN, BUILD, VERIFY, REVIEW and SHIP, with nine slash commands such as /spec, /plan, /build, /test, /review and /ship. The repo says the pack installs via the npx skills CLI into 70+ agents including Claude Code, Cursor, Codex and GitHub Copilot, with native plugin and local install paths; its README also notes that installing a single skill skips the repo-level references/ checklists, a portability gap tracked in issue #361.
At DevDay 2026, OpenAI pushed multi-agent work into its product line, launching Dots agents that can work around the clock: a personal Dot can call Codex for coding tasks, users and their Dots collaborate inside a shared Space, enterprise Specialist Dots take on specific duties, and an Agents API exposes harnesses, multi-agent control and computer-use capabilities to developers. OpenAI researcher Noam Brown, an early architect of o1 and later reasoning models, told podcast host Dwarkesh Patel that a system of 10,000 agents solved a Millennium Prize problem in 88 hours using about 130 billion tokens, but he would not credit even 10% of that to multi-agent coordination, saying a very strong general model did the real work. He said tests so far show 4 agents roughly doubling speed at double the cost, 16 agents behaving similarly but slightly less efficiently, gains running somewhat below linear and depending heavily on the task, and coordination efficiency at the 10,000-agent scale not yet well measured.
GitHub grew from roughly 100M users in early 2023 to 180M in September 2025 and past 225M by July 2026, according to Microsoft data cited by the article — growth that cannot be explained by professional developers alone. The piece argues that AI-lowered barriers have drawn in large numbers of non-technical users, spawning popular non-code projects such as classical Chinese poetry datasets, a "high-value life guide" that passed 27,000 stars in under a month, prompt libraries and "colleague.skill." GitHub itself has acknowledged that AI is driving interest in software development but said it "cannot fully explain the surge."
Stacklok, founded by Kubernetes creators Craig McLuckie and Joe Beda, pivoted from software supply chain security to Kubernetes-based agentic infrastructure. Its open source “cloud-native harness” Mecatl, started in June, separates the agent loop from tool execution, session management and memory; the companion open source project ToolHive runs and governs MCP servers on Kubernetes. The company says its AI Gateway is not yet open sourced but is on the roadmap, with an “enterprise spine” control plane as the commercial product.
OpenMontage has appeared on GitHub as a self-described first open-source, agentic video production system, bundling 12 production pipelines, 100+ tools and 700+ agent skill and production-knowledge files. It plugs into AI coding assistants such as Claude Code, Cursor, Copilot, Windsurf and Codex, letting an agent handle research, scripting, asset generation, editing and rendering using tools including Remotion, Blender, FFmpeg and Piper TTS. A local Backlot board turns the asset-generation contact sheet into an approval gate before the final render.
Cognee is an open-source AI memory platform that gives agents persistent long-term memory across sessions, turning documents, code and conversations into a self-hosted, searchable knowledge graph that can run locally with small models and no cloud LLM key. Per its release notes, v1.6.1 (September 24) bundles Google Drive and Gmail OAuth connectors into the SDK, streams visualization of large graphs in chunks, and moves the GLiNER installer off the event loop; v1.6.0 supports keyless memory building and retrieval. The project reports BEAM conversational-memory scores of 0.79 at 100K tokens and 0.67 at 10M tokens, while noting the two settings use different conversations, ingestion models and retrieval procedures.
Omnigent is an open-source AI agent framework and "meta-harness" that, per its project documentation, mixes Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and user-defined YAML agents in the same session, with sessions that follow you between terminal, browser, phone and a macOS desktop app. The README also claims support for first-party API keys or Claude/ChatGPT subscriptions, cloud sandboxes such as Modal, Daytona, E2B and Kubernetes, and policies that pause for approval, cap spend or limit tool access, plus session sharing for teammates. The repository is currently listed on GitHub Trending for Python.
text-to-cad is an agent plugin that adds local CAD workflows: it generates 3D models as STEP, GLB, STL or 3MF from plain-language or image requests, runs design-for-manufacturing checks, produces dimensioned engineering drawings, and connects to 3D printing, sheet metal and CNC fabrication services. It installs into Claude Code, Claude Desktop, Codex, Cursor, Gemini and Grok Build — any agent supporting plugins or the skills framework — or as skills alone via npx skills add; it runs through uv and downloads the cadgen runtime on first start. Skills cover CAD, off-the-shelf STEP parts, engineering drawings, DXF, URDF/SRDF, SDF, SendCutSend pre-upload checks, DfAM printability checks, OrcaSlicer G-code and Bambu Lab printing.
Diagram Design is a diagramming skill/plugin for agent hosts including Claude Code, Codex, GitHub Copilot, Factory Droid and Pi. It emits self-contained HTML + SVG with no build step, JavaScript or external image dependencies, and each visual type ships in minimal-light, minimal-dark and full-editorial variants. Creator Cathryn Lavery (LittleMight) added ten layout grammars in v2.5.10: Sankey, fishbone, Wardley map, kanban, user journey, deployment, dependency graph, UML class, story map and database schema. The skill can also read a website to match brand colors and redraw draw.io, Mermaid or Excalidraw sources at a chosen format, size and detail level; official builds come only from the repository.
What problem it solves
Developers using AI coding CLIs need a way to delegate work among multiple agents and coordinate their execution. CAO addresses this by running provider CLIs in isolated terminal sessions and giving a supervisor tools for coordinating workers.
Key features
Multi-agent delegation — A supervisor delegates work to specialist agents, with parallel and sequential execution suppor…
What problem it solves
Dodaios provides a locally installed, open-source way to make a personal AI assistant the control center for work on your computer. Its lead assistant coordinates models, coding agents, and computer use, while chats, memory, documents, and settings remain files on the computer that runs Dodaios.
Key features
Voice, chat, and phone interaction — The lead assistant supports wa…
What problem it solves
Web teams and developers can need to rebuild an existing site in a modern codebase when migrating platforms, recovering lost source code, or learning how a production site is constructed. This template gives an AI coding agent a repeatable workflow for recreating a site as an editable Next.js application while comparing its appearance and behavior with the source.
Key featur…
What problem it solves
Developers using multiple AI command-line tools need a consistent way to manage providers, accounts, prompts, MCP servers, sessions, and configuration. Switching configurations manually across applications can also make it difficult to inspect usage, preserve settings, or use different providers in separate terminal sessions.
Key features
Provider management — Manage API con…
What problem it solves
Shell users need a searchable, durable record of commands and terminal activity across machines, while AI agent users need continuity between sessions and harnesses. Atuin addresses both needs by recording terminal and agent activity and making it available for search, resumption, and optional synchronization.
Key features
Searchable shell history — Atuin records terminal ac…
What problem it solves
Coding agents can generate code without consistently applying a disciplined engineering workflow. Without reusable processes, teams may have to rebuild planning, testing, review, security, and learning practices in every prompt.
Key features
Coordinated engineering workflow — The system organizes agent work into a repeatable cycle that moves from planning and testing through…
What problem it solves
The project brings market monitoring, watchlists, portfolio records, research, news, backtesting, and report management into one workbench across China A-shares, US stocks, and HK stocks. It also keeps research records and imported materials on the user's computer while allowing research to be conducted with local AI subscriptions or compatible model APIs.
Key features
Unifi…
What problem it solves
AI agents often produce plausible SQL without the business definitions, approved joins, units, and examples needed to make results trustworthy. Teams also need a reviewable way to manage that context and turn governed answers into shareable dashboards across existing data sources.
Key features
Governed semantic and context layers — Business meaning is represented through the…
What problem it solves
Personal and team knowledge is distributed across notes, conversations, trackers, and research, making it difficult to capture, organize, verify, and synthesize useful information. COG provides a markdown-based workflow in which agents can maintain a shared knowledge base, support recurring research and operational tasks, and verify selected work through independent checks.
…
What problem it solves
Individual agents have different capabilities, context, workflows, and ecosystem connections, forcing users to switch interfaces, repeat information, and coordinate subtasks manually. Users need a way to delegate a task to appropriate installed agents and consolidate their work without managing each agent separately.
Key features
Automatic agent selection — AutoSwarm selects…
What problem it solves
Configurations for the Codex desktop app, CLI, API providers, prompts, Sessions, Skills, MCP, and TOML files can become scattered across multiple locations and formats. Codex-X consolidates these recurring configuration tasks into a visual desktop interface so the current state is visible and common operations can be completed directly.
Key features
Visual prompt management …
What problem it solves
Switching AI tools should not mean rebuilding or manually copying your setup. Teams also need a controlled way to version, share, audit, and distribute skills and other AI resources across projects and machines.
Key features
Unified resource management — Keep skills, agents, rules, MCP connections, hooks, and plugins in one place, then distribute them to the AI tools you use…
What problem it solves
AI agents need product-specific instructions to use NVIDIA software reliably across physical AI, robotics, simulation, CUDA-X libraries, RAG, and platform workflows. The catalog centralizes these skills while keeping them maintained in their respective product repositories and synchronized through an automated pipeline.
Key features
Agent-discoverable skill catalog — The NVI…
What problem it solves
Teams using coding agents need a shared way to access conversations, dispatch work, and follow activity across machines and surfaces. Screenshots, pasted logs, and separate agent sessions make context difficult to preserve and coordinate.
Key features
Shared agent conversations — Open the same conversation with teammates and follow its transcript, runtime status, files, and …
What problem it solves
Publishing videos, articles, and image posts across social media requires different platform-specific workflows and account preparation. Creators and operators need a consistent way to manage sessions and publish supported content through command-line and Agent-compatible interfaces.
Key features
Multi-platform publishing — Supports video, article, and image-post publishing …
What problem it solves
ChatGPT conversations need a controlled way to work with real project files, terminals, desktop applications, and long-running tasks. Users also need visibility, intervention, recovery, and session continuity when work is delegated across workers or spans multiple chats.
Key features
Local project and terminal control — ChatGPT can read and edit files, run tests, keep termin…
What problem it solves
Creating a complete character animation set requires more than generating isolated images: each action must be keyed, registered, timed, finished, and packaged for the target engine. Pixel-art workflows also need methods that convert model-generated flat artwork into consistent sprites on a real grid.
Key features
Complete sprite-set pipeline — Generate an approved master st…
What problem it solves
AI coding tools often expect particular provider protocols, making it difficult to use the models and providers a user prefers. A local gateway can translate between supported client APIs and provider APIs while preserving capabilities such as streaming, tool calls, reasoning, and images.
Key features
Provider protocol translation — The gateway translates Responses, Chat Com…
What problem it solves
Developers and coding agents need to understand how code is connected before making changes. GitNexus provides a graph-based view of symbols, callers, dependencies and execution flows to support code discovery, impact analysis and refactoring.
Key features
Graph-based code intelligence — Index a codebase as a knowledge graph covering symbols, calls, dependencies and executio…
What problem it solves
Agent memory is often opaque: stored context cannot be easily inspected or understood. OpenViking addresses this by organizing knowledge, memory, and skills in a browsable virtual filesystem, with summaries that help agents identify relevant context before reading full files.
Key features
Unified context filesystem — Knowledge, memory, and skills share one filesystem address…