AICoder

AI Coding Live News

First-hand AI coding updates from 𝕏/Twitter frontier labs and researchers, distilled by AI with entity benchmarks.

Explore live on 𝕏 ↗

AI Coding Live News

T
Thomas Dohmke@ashtom·
👀72
🔥86
View on 𝕏 ↗

Entire, led by ex-GitHub CEO Thomas Dohmke, launches a Git forge for agent-human collaboration: Trails replace PRs, pushes up to 89x faster than GitHub per its benchmarks

On Oct 26, Entire co-founder and CEO Thomas Dohmke announced on X and the company blog that Entire is live as "the Git forge for agent-human collaboration." It has three parts: Trails, which replace diff-based review with eval scores computed on every push; Git-compatible distributed hosting that can replicate across regions or mirror from GitHub; and Continuous Memory, which stores agent sessions in the repo. Buildkite and Depot are the first CI integrations, and it is open to any developer today.

Entire, led by ex-GitHub CEO Thomas Dohmke, launches a Git forge for agent-human collaboration: Trails replace PRs, pushes up to 89x faster than GitHub per its benchmarks

Key Takeaways

  • Push speed (vendor-reported, open-source benchmark): Entire 418 pushes/s vs Cursor Origin 65, Pierre 15, GitLab 10, GitHub 4.7, i.e. up to 89x faster than GitHub and 6x faster than Cursor Origin
  • Trails: on every push, several review agents score the change independently in cloud sandboxes (defaults include Security, Slop and Human Review Required), showing the last 5 runs plus the current one; per-repo Gates can require human approval and passing CI before merge
  • Continuous Memory: two open-source, local-first plugins, entire-graph and entire-brain; entire-graph saved up to 71% of tokens in Entire's testing
  • Regions at launch: US, EU, Australia and India; repos can be mirrored from GitHub with GitHub kept as the source of truth
  • Pricing: not stated in the launch post
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🤖 codex🌐 entire
#Entire#Thomas Dohmke#Git forge#Trails#Continuous Memory#Code review#Buildkite#Depot
P
PyTorchPyTorch·
👀85
🔥87
View on 𝕏 ↗

Google and Meta open-source TorchTPU: native PyTorch on TPUs, where porting is as simple as .to("cuda") to .to("tpu"), with native TPU backends for vLLM and SGLang

At PyTorch Conference 2026 on Oct 20, Google open-sourced TorchTPU on GitHub, co-developed with Meta's PyTorch team, making TPUs a native PyTorch device alongside GPUs and CPUs: eager mode and torch.compile, about 450 ATen ops, and torch.distributed collectives. Google also released vLLM-TorchTPU and SGLang-TorchTPU engines, integrations with TorchTitan, Ray, VeRL and Hugging Face Transformers v5 (device_map="tpu"), and a preview TPU agent suite for coding assistants such as Claude Code and Antigravity. AWS shipped the comparable TorchNeuron a day earlier.

Google and Meta open-source TorchTPU: native PyTorch on TPUs, where porting is as simple as .to("cuda") to .to("tpu"), with native TPU backends for vLLM and SGLang

Key Takeaways

  • Porting (official PyTorch blog): existing code runs by changing model.to("cuda") to model.to("tpu") and the distributed backend to tpu_dist; the team notes peak TPU performance still needs TPU-aware shapes and sharding
  • Coverage (vendor-reported): 98% of about 4,917 popular Hugging Face models (4,821) run without crashing, and 97% of 657 architecture representatives (638) match GPU numerics
  • Training scale (vendor-reported): Qwen3 MoE 235B on TorchTitan scales from 1,024 to 8,192 TPU v7 chips with MFU roughly flat at 27-29%; on 64 TPU v7 chips it reaches 1,828 TPS versus 1,937 TPS for JAX/MaxText
  • Inference cost (Google citing SemiAnalysis InferenceX): TPU v7 with vLLM-TorchTPU hits 2.01 cents per million tokens on 8K/1K, down from 3.6 cents at its September debut
  • Four repos open-sourced: torch_tpu, vllm-torchtpu, sglang-torchtpu and a TPU TorchTitan; the TPU agent suite is in preview for TPU v6e and TPU7x
Read full story
Linked Models & Agents:
⚡ Qwen3 MoE 235B⚡ Llama 3 405B⚡ Muse Glimmer 30B⚡ Qwen 3.5🤖 TPU agent suite🤖 Claude Code🤖 Google Antigravity🌐 Google🌐 Google Cloud🌐 Meta🌐 Hugging Face🌐 Inferact🌐 RadixArk🌐 Anyscale
#TorchTPU#PyTorch#TPU#vLLM#SGLang#TorchTitan#PyTorch Conference
F
Figma@figma·
👀88
🔥84
View on 𝕏 ↗

Figma Config India: Code Layers and Specs enter open beta, and agents can read and write specs and code layers through the Figma MCP server

At Config India on 2026-10-15 Figma launched agent-oriented features: Code Layers (running code on the canvas) in open beta on all plans, Specs (collaborative Markdown spec containers) in open beta on paid plans, Guidelines in open beta and Code Sources in closed beta. The Figma MCP server can now generate code layers and read/write Specs, with 20 new MCP partner integrations including OpenCode and JetBrains Junie.

Figma Config India: Code Layers and Specs enter open beta, and agents can read and write specs and code layers through the Figma MCP server

Key Takeaways

  • Code Layers: open beta on all plans, created from designs, local folders, GitHub, MCP or Chrome-extension page capture; uses AI credits, free on paid plans through 2026-11-04
  • Specs: open beta on Professional/Organization/Enterprise across web, desktop and mobile; pasting a Spec link into a coding agent carries Markdown, frame references, code layers and Code Connect snippets
  • MCP: the figma-spec skill lets agents read, create and update Specs; use_figma canvas writes remain a free beta with up to 20 KB output per call
  • Design systems: Guidelines open beta and Code Sources closed beta (import from a GitHub repo or npm package) on paid plans; Payload lands in Figma Make, with downloads up 6x in 12 months per Figma
  • Ecosystem: 20 new MCP partner integrations including OpenCode, Dia, JetBrains Junie and Meta Muse; the Figma agent is generally available
Read full story
Linked Models & Agents:
🤖 Figma agent🤖 OpenCode🤖 Junie🌐 Figma🌐 JetBrains🌐 Payload
#Figma#Config India#Code Layers#Specs#MCP#Design to code#coding agents
C
Cursor@cursor_ai·
👀73
🔥85
View on 𝕏 ↗

Cursor launches the Origin App Marketplace with 20+ CI, deploy, code-review and security integrations, open to public submissions

On Oct 13 Cursor launched the Origin App Marketplace: its code hosting platform Origin now connects to 20+ apps across deployments (Cloudflare, Vercel and more), CI (CircleCI, Buildkite and more), code review (CodeRabbit, Greptile, Tenki), security (Semgrep, Socket and more), monitoring (Sentry) and project management (Linear), and the marketplace is open to public submissions from any developer-tool team.

Cursor launches the Origin App Marketplace with 20+ CI, deploy, code-review and security integrations, open to public submissions

Key Takeaways

  • 21 launch apps in 6 categories: deploy (5), CI (7), code review (3), security (4), monitoring (1), project management (1)
  • Public submissions: build privately in your namespace, make it public, submit with slug, tags and a demo video, then Cursor reviews and lists it
  • Apps authenticate with an app JWT plus installation access tokens, receive webhooks, and write back check runs, PR comments and reviews
  • The official origin-apps plugin answers questions from live Origin API docs and plans ports of existing apps
  • Launch post: ~1,356 likes and ~68K views as of Oct 14 morning
Read full story
Linked Models & Agents:
🤖 Cursor🌐 Cursor🌐 Cloudflare🌐 Vercel🌐 Sentry🌐 Linear🌐 CodeRabbit🌐 Greptile
#Cursor#Origin#Marketplace#CI/CD#code review#DevSecOps#source control#Integrations
ADSponsored
G
GitHub@github·
👀73
🔥94

GitHub Spec Kit 1.0.12: Bitbucket auth, Agentstandards community packs, taskstoissues deprecation notice

GitHub Spec Kit (specify-cli) shipped v1.0.12 on 2026-09-25: Bitbucket auth provider; community catalog gains Agentstandards bundle, Task Gate preset, and Architecture Council extension; SpecAssay/Intake presets updated. Core /speckit.taskstoissues is slated to leave core for a bundled github extension. Install via uv tool install specify-cli then specify init with Copilot or other integrations.

GitHub Spec Kit 1.0.12: Bitbucket auth, Agentstandards community packs, taskstoissues deprecation notice

Key Takeaways

  • Shipped: v1.0.12 / PyPI specify-cli 1.0.12; repo ~139k stars
  • Install: uv tool install specify-cli; specify init --integration copilot (or other keys)
  • Adds Bitbucket auth; Agentstandards / Task Gate / Architecture Council in community catalog
  • Upcoming: /speckit.taskstoissues moves out of core to bundled github extension
  • Fixes: multi-arg filter rejection, catalog_fetch TOCTOU, Alquimia skills-only rendering
Read full story
Linked Models & Agents:
🤖 GitHub-Copilot🤖 Claude-Code🤖 Codex🤖 Spec-Kit🌐 GitHub
#Spec-Kit#SDD#Specify CLI#Bitbucket#Agentstandards#Copilot#Uv
B
ByteDance@bytedance·
👀97
🔥95

ByteDance Releases DeerFlow 2.0: Ground-Up Rewrite of 83K-Star Long-Horizon SuperAgent Harness

ByteDance launched DeerFlow 2.0.0, completing a ground-up rewrite of its 83k-star open-source agent harness with 182 merged PRs. Built around a SuperAgent architecture, DeerFlow 2.0 orchestrates sub-agents, persistent memory, and sandboxed execution with extensible tools. It introduces self-updating SOUL memory, user-owned IM channel integrations (Feishu, DingTalk, WeChat, Slack, Discord, Telegram), Docker DooD sandbox protection, and deep integration with BytePlus InfoQuest crawling technology for robust multi-hour autonomous execution.

ByteDance Releases DeerFlow 2.0: Ground-Up Rewrite of 83K-Star Long-Horizon SuperAgent Harness

Key Takeaways

  • Full architectural rewrite: migrated from rigid workflows to a SuperAgent harness orchestrating sub-agents, memory, and sandboxes
  • Evolving agent souls: agents can modify and persist their own SOUL.md and YAML configs across chats with strict user isolation
  • Universal IM gateway: native support for Feishu/Lark, DingTalk, WeChat/WeCom, Slack, Discord, and Telegram integrations
  • Enterprise-grade sandbox: DooD Docker isolation with automated zip-bomb protection and sensitive MCP credential masking
  • Production observability: Langfuse distributed tracing with parent-child attribution and thread-indexed O(1) query acceleration
Read full story
Linked Models & Agents:
⚡ Doubao Seed 2.0 Code⚡ DeepSeek-V3⚡ Kimi 2.5🤖 DeerFlow🤖 SuperAgent🌐 ByteDance🌐 Volcengine🌐 BytePlus
#DeerFlow#ByteDance#SuperAgent#SubAgents#Docker Sandbox#MCP#IM Gateway
P
Prime Intellect@PrimeIntellect·
👀75
🔥88
View on 𝕏 ↗

Prime Intellect opens Prime Sandboxes: MicroVMs for agentic RL, claimed ~3× cheaper

Prime Intellect (@PrimeIntellect) GA’d Prime Sandboxes—hardware-virtualized MicroVMs for agentic RL. Full Linux VM fidelity (Docker Compose, background jobs, kernel workloads), elastic to tens of thousands concurrent, with verifiers/prime-rl/Prime Tunnels integrations and 365k+ prebuilt environments. Blog: ~30M sandboxes created internally; default 1,024 concurrent; tier-free pricing claimed ~3× cheaper than peers through Dec 22 (e.g. vCPU $0.02/hr).

Prime Intellect opens Prime Sandboxes: MicroVMs for agentic RL, claimed ~3× cheaper

Key Takeaways

  • Blog: hardware MicroVMs with guest kernels vs gVisor—better for Docker Compose and system-level agent envs.
  • ~30M sandboxes created internally; product page shows live concurrent/total counters.
  • 365,000+ prebuilt envs; verifiers / prime-rl integrations.
  • Default 1,024 concurrent; sample price vCPU $0.02/hr, RAM $0.0125/GiB/hr; claimed ~3× cheaper through 2026-12-22.
  • CLI: prime sandbox create / run; docs: sandboxes overview.
Read full story
Linked Models & Agents:
🤖 prime-sandboxes🤖 prime-rl🌐 prime-intellect
#Prime Intellect#Sandboxes#MicroVM#RL#agentic training#Verifiers#Docker
D
Dan Kornas@DanKornas·
👀57
🔥90
View on 𝕏 ↗

Xpert open-sources a governed plugin platform for models, tools, skills, and agent apps

@DanKornas highlighted Xpert, an open-source agent platform with one governed plugin lifecycle for models, integrations, tools, middleware, skills, and apps. Agent Studio configures agents visually; hybrid agent-workflow paths and Docker Compose self-hosting. AGPL-3.0. github.com/xpert-ai/xpert

Key Takeaways

  • Governed plugins for models, tools, middleware, skills, and apps.
  • Agent Studio plus hybrid agent/workflow paths.
  • Docker Compose self-hosting; open-source AGPL-3.0.
Read full story
Linked Models & Agents:
#Xpert#agent platform#Plugins#Skills#Agent Studio#Self host#open source
R
Replit@Replit·
👀46
🔥89
View on 𝕏 ↗

Replit Custom Connectors enter beta for governed REST API integrations

Replit announced Custom Connectors are in beta, letting workspace administrators connect supported publicly accessible HTTPS REST APIs with API-key authentication without waiting for first-party connectors. The governed integration path expands the systems Replit AI coding workspaces can use while keeping configuration under admin control.

Key Takeaways

  • Workspace administrators can configure supported publicly accessible HTTPS REST APIs with API-key authentication.
  • Custom Connectors let teams connect internal tools and specialized services without waiting for first-party integrations.
  • The governed workspace model provides a practical path for connecting enterprise systems to Replit AI coding workflows.
Read full story
Linked Models & Agents:
#Replit#Custom Connectors#REST API#API Key#AI coding#workspace integrations
S
Sagar Tanur@Sagarvd01·
👀37
🔥87
View on 𝕏 ↗

Claude Managed Agents ships auto permission policy: server decides run, deny, or pause per agent/MCP call

Developer Sagar Tanur (@Sagarvd01) reports Claude Managed Agents shipped an auto permission policy: the server evaluates each agent/MCP tool call and chooses run, deny, or pause. He notes MCP toolsets still default to always_ask, which matters more for real integrations than demos.

Key Takeaways

  • Managed Agents adds auto permissions: server chooses run/deny/pause per tool call.
  • Server-side policy for agent and MCP calls reduces manual per-call prompts.
  • MCP toolsets still default to always_ask—check this when integrating.
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🌐 Anthropic
#Claude#Managed Agents#MCP#Permissions#Auto#Anthropic
ADSponsored
E
Elon Musk@elonmusk·
👀42
🔥90
View on 𝕏 ↗

Grok Bot Integrates with Salesforce, HubSpot, and Major GTM Tooling

xAI upgraded Grok Bot for sales teams with native integrations across Salesforce, HubSpot, Gong, Clay, and Granola, enabling autonomous customer research, meeting follow-ups, and CRM workflows.

Key Takeaways

  • Deep enterprise integrations across Salesforce, HubSpot, Gong, Clay, and Granola
  • Automates CRM lead enrichment, post-call action items, and pipeline hygiene
  • Evolves Grok Bot from chatbot into an autonomous enterprise workforce agent
Read full story
Linked Models & Agents:
⚡ Grok Bot🤖 Grok Bot Sales Agent🌐 xAI🌐 Salesforce
#xAI#Grok Bot#Salesforce#GTM#AI Agent
@
@elonmusk@elonmusk·
👀35
🔥88
View on 𝕏 ↗

Grok Bot adds sales-tool integrations

Elon Musk amplified a Grok Bot update for sales teams. Bots can now connect to Salesforce, HubSpot, Gong, Clay, Granola, and other GTM tools to track accounts, complete follow-ups, and run deep research.

Key Takeaways

  • Elon Musk amplified a Grok Bot update for sales teams. Bots can now connect to Salesforce, HubSpot, Gong, Clay, Granola, and other GTM tools to track accounts, complete follow-ups, and run deep research.
Read full story
Linked Models & Agents:
#AI#LLM#Coding
G
GitHub@github·
👀46
🔥92
View on 𝕏 ↗

GitHub Copilot generally available with Gemini 3.7 Flash, MAI-Code-1.1-Flash, and Kimi K3

GitHub said Gemini 3.7 Flash, Microsoft MAI-Code-1.1-Flash, and the Fireworks-hosted open-weight Kimi K3 model are generally available in the GitHub Copilot app, Copilot CLI, VS Code, and related surfaces. Developers can switch among Google's low-cost coding model, Microsoft's in-house code model, and an open-weight option without leaving the Copilot workflow. The same Copilot weekly thread also promoted a Customize tab that gathers MCP servers, plugins, skills, and canvases, plus Slack and Microsoft Teams integrations that let teams mention GitHub to plan changes, investigate problems, and hand off coding tasks from chat. For organizations standardizing on GitHub as the agent control plane, the release is less about a single SOTA model and more about routing: pick Gemini 3.7 Flash for cheap iteration, MAI-Code for Microsoft-stack tasks, or Kimi K3 when open weights and Fireworks hosting matter.

Key Takeaways

  • Gemini 3.7 Flash, MAI-Code-1.1-Flash, and Kimi K3 are GA in Copilot app, CLI, and VS Code.
  • Kimi K3 lands as a Fireworks-hosted open-weight option inside Copilot.
  • Teams can route tasks across closed-source efficiency models and open weights, including from Slack and Teams.
Read full story
Linked Models & Agents:
⚡ Gemini 3.7 Flash⚡ Kimi K3🌐 Microsoft Azure AI🌐 Google DeepMind🌐 Moonshot AI (月之暗面)
#Github copilot#Gemini 3 7 flash#Mai code#Kimi k3#Vscode
G
GitHub@github·
👀62
🔥90
View on 𝕏 ↗

GitHub Copilot lands in Slack and Microsoft Teams for in-chat planning, incident triage, and agent handoff

GitHub launched Copilot integrations for Slack and Microsoft Teams. Teammates can mention @GitHub in the channels where work is already coordinated to plan changes, investigate problems, and hand coding tasks to agents. The update embeds agentic work in existing chat surfaces instead of forcing a context switch back to the IDE.

Key Takeaways

  • Mention @GitHub in Slack or Teams to plan diffs, investigate issues, and hand off coding tasks.
  • Agentic work starts in the chat surface teams already use, cutting IDE context switches.
  • Fits on-call, review, and requirements threads that need an agent without leaving the channel.
Read full story
Linked Models & Agents:
🌐 Microsoft Azure AI
#Github copilot#Slack#Microsoft teams#Agents#Collaboration
C
Cursor@cursor_ai·
👀32
🔥98
View on 𝕏 ↗

Cursor Launches Origin Git Hosting Platform: Native In-Editor Code Collaboration for Cloud Agents

Cursor unveiled Origin, its native Git hosting platform engineered for high-speed agentic code collaboration with seamless GitHub repo syncing and day-1 CI/CD integrations with Vercel and Buildkite.

Key Takeaways

  • Cursor expands beyond the editor layer into core repository hosting infrastructure;
  • Supports frictionless two-way syncing with existing GitHub repositories for low-risk adoption;
  • Day-1 CI/CD integration with Vercel, Buildkite, and Depot enables instant build and deployment loops.
Read full story
Linked Models & Agents:
⚡ Claude 3.7 Sonnet (Hybrid Reasoning)