AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs — AICoder

Ivan Leoivanleomk·Collected 5h ago

👀10

🔥86

View on 𝕏 ↗

Google Antigravity Launches Remote Agents: Agent Sessions Run in a Google-Managed Cloud Environment and Keep Working After You Close Your Laptop, Rolling Out to AI Pro and Ultra

Ivan Leo, who works on developer experience at Google DeepMind, shared the official docs for Antigravity's new Remote Agents feature on X on November 4. Per the docs, Remote Agents run agent sessions and tools in an isolated, Google-managed remote environment, so tasks keep going when you close your laptop or browser or switch between desktop and mobile. Sessions start from the Antigravity App, the Antigravity CLI (1.4.12+, agy --remote-agent) or the web at antigravity.google.com, and remote projects can attach GitHub repositories, Google Drive files and uploads. It is rolling out gradually to Google AI Pro and Ultra subscribers on personal accounts; it is not available on the free plan, AI Plus or business accounts.

Key Takeaways

Remote Agents run in an isolated Google-managed environment with no local machine required; Remote Control instead connects to your own computer or server, and the web sidebar switches between them.
Three entry points: a New Remote Project in the Antigravity App, agy --remote-agent in CLI 1.4.12+, or antigravity.google.com in any browser, including mobile.
Remote projects can attach GitHub repositories (cloned automatically), Google Drive files and uploads (8 MiB per file, 100 MiB per project, 2 GiB per account).
CLI remote sessions default to the always-proceed (turbo) permission preset, so commands run without approval; locally installed MCP servers, plugins and skills are not available remotely yet.
Only for Google AI Pro and Ultra subscribers on personal accounts, rolling out gradually; not on the free plan, AI Plus or Workspace/Cloud business accounts.

Read full story

Linked Models & Agents:

🤖 Google Antigravity 🤖 Antigravity CLI 🌐 Google 🌐 Google DeepMind

#Antigravity#Remote Agents#cloud agents#coding agent#Google

Kaggle@kaggle·Collected 5d ago

👀45

🔥81

View on 𝕏 ↗

Kaggle and IBM Research launch the ScarfBench Java migration leaderboard: Gemini 4 Argon with Antigravity leads at 75.2%, and about 72% of failures happen at runtime

Kaggle announced ScarfBench with IBM Research, a 204-task benchmark that tests whether coding agents can migrate enterprise Java apps between Jakarta EE, Quarkus and Spring without changing behavior. IBM's October 27 technical note shows Gemini 4 Argon with Antigravity first on the smoke score at 75.2%, Claude Opus 5.5 with Claude Code highest on all-tests-pass at 72.1%, and GPT-6.1 Sol with Codex cheapest at $1.25 per solved task.

Kaggle and IBM Research launch the ScarfBench Java migration leaderboard: Gemini 4 Argon with Antigravity leads at 75.2%, and about 72% of failures happen at runtime

Key Takeaways

204 migration tasks and 10 model-plus-harness configurations; top smoke scores are Gemini 4 Argon + Antigravity 75.2%, Claude Opus 5.5 + Claude Code 70.5% and Claude Opus 5 + Claude Code 69.8% (IBM figures)
Claude Opus 5.5 + Claude Code has the highest all-tests-pass rate at 72.1%, just ahead of Gemini 4 Argon at 71.1%
Compiling is mostly solved: 8 of 10 configurations compiled at least 97% of solvable tasks, yet smoke scores spanned more than 50 points
535 of 745 classified failing runs (about 72%) were runtime behavioral failures, including 210 lost-route/404 failures
Cost per solved task: $1.25 for GPT-6.1 Sol + Codex, $1.59 for Gemini 3.8 Flash + mini-swe and $10.10 for Claude Opus 5.5 + Claude Code; public submissions are not open yet

Read full story

#ScarfBench#Kaggle#IBM Research#Benchmark#coding agents#Java#Spring#Quarkus#Jakarta EE#Migration

Jules@julesagent·Collected 6d ago

👀58

🔥84

View on 𝕏 ↗

Google is winding down its async coding agent Jules: read-only after Nov 11 and shut down on Dec 31, with its learnings moving into Antigravity

On Oct 29, Google announced through the official @julesagent account and the Jules changelog that Jules will wind down on December 31, 2026. Users can keep finishing sessions until November 11, after which Jules becomes read-only until the end of the year. Google says its learnings from Jules are going into Google Antigravity, its agent-first development platform, to combine autonomous remote background task execution with an agent-first environment. Google also published an export path for settings, environment variables, scheduled tasks, repositories, memories and every session.

Key Takeaways

Key dates: sessions can run until Nov 11, then Jules is read-only, and it shuts down on Dec 31
Next stop: Jules learnings go into Google Antigravity; Google does not promise automatic migration of sessions, memories or schedules
Export: run npm install -g @google/jules and jules login, then paste the official export prompt into a CLI coding agent; data lands in ~/jules-export
Code, branches and PRs already live in GitHub and are unaffected; env-variables.json holds secrets, so keep the export folder out of repos

Read full story

Linked Models & Agents:

🤖 Jules 🤖 Google Antigravity 🌐 Google

#Jules#Google Antigravity#coding agents#async agents#Shutdown#Migration

Android StudioAndroidStudio·Collected 6d ago

👀68

🔥83

View on 𝕏 ↗

Android Studio Rabbit 2 goes stable with Bring Your Own Agent: 40+ coding agents including Claude Agent, Codex and Antigravity via the open ACP

On Oct 28, the day of Android Dev Summit, Google shipped Android Studio Rabbit 2 (2026.2.2) to the stable channel. The headline change is that Bring Your Own Agent (BYOA) moves from its September Canary preview to a stable feature: developers can plug any Agent Client Protocol (ACP) compatible coding agent into the IDE agent window. Google says more than 40 are available, including Anthropic Claude Agent, OpenAI Codex, JetBrains Junie and Google Antigravity, and users can sign in with personal or enterprise plans. The release also adds an agent skills manager, AI Change Review and agent-assisted LeakCanary fixes.

Android Studio Rabbit 2 goes stable with Bring Your Own Agent: 40+ coding agents including Claude Agent, Codex and Antigravity via the open ACP

Key Takeaways

Version 2026.2.2 reached the Stable channel on Oct 28; BYOA first appeared in preview with the Rabbit 2 Canary in September
Google says 40+ ACP-compatible agents are available; Claude Agent, Codex and Antigravity are the defaults, and others install from the registry under Settings > Tools > AI > Agents
Agents get IDE tools: the project graph and build diagnostics, Android SDK tools, terminal execution, emulator control, Logcat and Compose Preview
Sign in with personal API keys or consumer and enterprise subscriptions; the built-in Android Studio agent stays free
Also new: a skills manager preloaded with Android and Firebase skills, AI Change Review from three entry points, and agent-assisted LeakCanary fixes; Google's Mishaal Rahman said Android CLI users grew 10x

Read full story

Linked Models & Agents:

🤖 Claude Agent 🤖 Codex 🤖 Antigravity 🤖 Junie 🌐 Google 🌐 Anthropic 🌐 OpenAI 🌐 JetBrains

#Android Studio#BYOA#ACP#coding agents#IDE

Qiuyang MangMangQiuyang·Collected 9d ago

👀35

🔥86

View on 𝕏 ↗

FrontierCS 2 benchmark: agents must rebuild a paper's deleted contribution in its own repo and beat the authors' code; Claude Opus 5.5 leads at 58%, 16 tasks unsolved

Teams from UC Berkeley, Princeton and others released FrontierCS 2 (arXiv 2610.29932): 48 tasks across 13 CS domains, each built by deleting a paper's contribution from the authors' released code. An agent has 5 hours to write it back and passes only if it beats the original on every metric and every hidden workload. Of 12 agents, Claude Opus 5.5 in Claude Code leads with a 58% pass rate, every other agent passes fewer than half, and 16 tasks have no passing run. On Oct 26 maintainer Wenhao Chai said a trace audit showed the Pi harness ends runs on refusals; rerun in Antigravity, Gemini 4 Argon now beats GPT-6 Astra and sits right behind Opus 5.5.

Key Takeaways

48 tasks, 13 domains, 12 agents, one run per agent per task (paper)
Strict pass rule: the final submission must beat the authors' code on every metric and every hidden workload; a higher total score can still fail
Claude Opus 5.5 in Claude Code leads with a 58% pass rate; 16 tasks have no passing run
Under the Pi harness, 10 of Gemini 4 Argon's 48 runs ended on provider refusals; rerun in Antigravity it beats GPT-6 Astra (Wenhao Chai's post)
Tasks and evaluators are open source on GitHub; the authors estimate a full 48-task run with Opus 5.5 at about $1,000 in API fees, $300 GPU and $100 CPU

Read full story

Linked Models & Agents:

⚡ Claude Opus 5.5 ⚡ GPT-6 Astra ⚡ GPT-6.1 Sol ⚡ Gemini 4 Argon ⚡ DeepSeek-V4.1-Flash⚡ Kimi K2.7🤖 Claude Code 🤖 Codex CLI 🤖 Antigravity 🤖 Pi 🌐 Anthropic 🌐 OpenAI 🌐 Google DeepMind 🌐 UC Berkeley 🌐 Princeton

#FrontierCS 2#Benchmark#Agent#CS research#Harness#FCI

OpenAIOpenAI·Collected 14d ago

👀67

🔥88

View on 𝕏 ↗

OpenAI frontier models and Codex are coming to Google Cloud: Model Garden access, bought via Marketplace against existing GCP commitments

On Oct 21, OpenAI and Google Cloud announced a partnership bringing OpenAI frontier models and Codex agentic workflows into Google Cloud Model Garden, transacted through Google Cloud Marketplace so enterprises can draw down existing GCP commitments. OpenAI models will also come to Google Antigravity and Gemini Agent soon. General availability is planned in the coming weeks, and Microsoft remains OpenAI's primary cloud partner. After AWS, this puts OpenAI models on all three major US clouds.

OpenAI frontier models and Codex are coming to Google Cloud: Model Garden access, bought via Marketplace against existing GCP commitments

Key Takeaways

Channel: OpenAI frontier models and Codex come to Google Cloud Model Garden, transacted through Google Cloud Marketplace (official)
Procurement: enterprises can draw down existing GCP commitments, no separate OpenAI contract or invoice
Ecosystem: OpenAI models are coming soon to Google Antigravity and Gemini Agent, selectable alongside Gemini
Timing: GA planned in the coming weeks, access requests open now; Microsoft remains the primary cloud partner
Landscape: after Microsoft exclusivity ended in April and AWS added OpenAI models, OpenAI is now on all three major US clouds (per Reuters/CNBC)

Read full story

Linked Models & Agents:

⚡ GPT-6 Astra ⚡ GPT-6.1 Sol ⚡ GPT-6 Luna 🤖 codex 🌐 OpenAI 🌐 Google Cloud 🌐 Google 🌐 Microsoft

#OpenAI#Google-Cloud#Model-Garden#Codex#Antigravity#Enterprise#Multi cloud

PyTorchPyTorch·Collected 15d ago

👀87

🔥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

Cognitioncognition·Collected 16d ago

👀142

🔥84

View on 𝕏 ↗

Devin Fusion with an Opus 5.5 lead and GPT-6 Luna sidekick tops the Artificial Analysis Coding Agent Index at 68.1, at what Cognition says is 31% lower cost per task than Claude Code with Opus 5.5

Cognition said on October 19 that Devin Fusion, pairing Claude Opus 5.5 as the lead with GPT-6 Luna as the sidekick, scored 68.1 on the Artificial Analysis Coding Agent Index v1.5. Artificial Analysis's current data puts it first, but only 0.1 ahead of Muse Code with Muse Wonder Full at 68.0, effectively a tie; Antigravity CLI with Gemini 4 Argon is third at 63.8. Cognition says the pairing costs 31% less per task than Claude Code with Opus 5.5 (vendor-reported). Fusion ships in Devin CLI and Desktop.

Devin Fusion with an Opus 5.5 lead and GPT-6 Luna sidekick tops the Artificial Analysis Coding Agent Index at 68.1, at what Cognition says is 31% lower cost per task than Claude Code with Opus 5.5

Key Takeaways

68.1 overall: DeepSWE v1.1 72.6, SWE-Atlas-QnA 69.6, Terminal-Bench v4 62.1, equally weighted (Artificial Analysis data).
Just 0.1 ahead of Muse Code with Muse Wonder Full (68.0); Antigravity CLI with Gemini 4 Argon 63.8, Codex with GPT-6.1 Sol (xhigh) 62.9.
Cost: Cognition says 31% lower per task than Claude Code with Opus 5.5 (vendor-reported).
Earlier, Fusion with Fable 5.1 + SWE-2 cut DeepSWE 1.1 cost per task from $14.63 to $7.88 (-46%) while scoring 63.1 vs 64.3.
Recommended pairing is Opus 5.5 + GPT-6 Luna, available by installing Devin CLI.

Read full story

Linked Models & Agents:

⚡ Claude Opus 5.5 ⚡ GPT-6 Luna ⚡ Muse Wonder ⚡ Gemini 4 Argon ⚡ GPT-6.1 Sol 🤖 Devin 🤖 Claude Code 🤖 Muse Code 🤖 Antigravity CLI 🤖 Codex 🌐 Cognition 🌐 Anthropic 🌐 OpenAI 🌐 Meta 🌐 Google 🌐 Artificial Analysis

#Devin#Fusion#Artificial Analysis#Coding Agent Index#Benchmark

Artificial Analysis@ArtificialAnlys·Collected 21d ago

👀154

🔥89

View on 𝕏 ↗

Artificial Analysis launches AA-Robotics v0.1: coding agents drive a real robot arm, GPT-6 Astra leads at 69.4

Artificial Analysis released AA-Robotics v0.1 on 2026-10-14, a research preview in which frontier models running inside coding-agent harnesses (Codex, Claude Code, Antigravity) control a 6-axis robot arm over an HTTP API across eight tabletop tasks. GPT-6 Astra scores 69.4, ahead of GPT-6.1 Sol (64.6), Gemini 4 Argon (55.3), Claude Opus 5.5 (48.8) and Claude Fable 5.1 (46.3). Models take about 30 minutes per task versus roughly 20 seconds for a human.

Artificial Analysis launches AA-Robotics v0.1: coding agents drive a real robot arm, GPT-6 Astra leads at 69.4

Key Takeaways

Scores (out of 100): GPT-6 Astra 69.4, GPT-6.1 Sol 64.6, Gemini 4 Argon 55.3, Claude Opus 5.5 48.8, Claude Fable 5.1 46.3 (AA article)
Speed: ~30 min per task for models (Argon ~52 min) vs ~20 s for a human
Cost: GPT-6.1 Sol cheapest at $1.93/task, GPT-6 Astra $16.36/task; ~70% of spend is input context
Grasp success: Astra 45%, Fable 5.1 44%, Opus 5.5 40%, Argon 36%, Sol 28%
Measure-the-box (within 2 mm) tops out at 17/100 across all five models

Read full story

Linked Models & Agents:

⚡ GPT-6 Astra ⚡ GPT-6.1 Sol ⚡ Gemini 4 Argon ⚡ Claude Opus 5.5 ⚡ Claude Fable 5.1 🤖 codex 🤖 Claude Code (Anthropic)🤖 Google Antigravity (AGY)🌐 artificial-analysis 🌐 OpenAI 🌐 Google DeepMind 🌐 Anthropic

#AA-Robotics#Artificial Analysis#Benchmark#GPT-6 Astra#Codex#Claude Code#Antigravity

haofan@haofan·Collected 21d ago

👀257

🔥86

Antigravity CLI 1.3.5: Auto mode auto-approves safe edits and commands, reviews sandbox escapes via a separate agent, and adds /compact

Google Antigravity CLI shipped 1.3.5 on 2026-10-14 (UTC). Release notes add Auto mode: it auto-approves file edits and safe commands, still prompts before irreversible actions, and sends commands that would leave the terminal sandbox to a separate agent for review first. Enable with --mode auto, Agent Mode in /config, or Shift+Tab; Linux and macOS now, Windows later. The same cut adds on-demand /compact and upgrades /diff with syntax highlighting, folding, and viewport rendering for large files. Official modes docs still listed only default / accept-edits / plan at fetch time—treat the GitHub release as source of truth.

Antigravity CLI 1.3.5: Auto mode auto-approves safe edits and commands, reviews sandbox escapes via a separate agent, and adds /compact

Key Takeaways

Release: Antigravity CLI 1.3.5 (89081f7, 2026-10-14T03:16:53Z) leads with Auto mode
Auto: auto-approves file edits and safe commands; still prompts before irreversible actions; sandbox-leaving commands are reviewed by a separate agent first (per GitHub release)
Enable via --mode auto, Agent Mode in /config, or Shift+Tab; Linux/macOS now, Windows later
/compact on demand: alone summarizes and ends the turn; with a follow-up it summarizes then answers; Esc cancels; finish shows steps summarized and context shrinkage
/diff: syntax highlighting, hunk folding (Ctrl+O / f), viewport rendering; expand-all disabled over 100k lines or 10 MB

Read full story

Linked Models & Agents:

⚡ Gemini 4 Argon 🤖 Antigravity CLI 🤖 agy 🌐 Google 🌐 Google DeepMind

#Antigravity#Antigravity CLI#Agy#Auto mode#Compact#Sandbox#Google#CLI#Agent#1.3.5

Google DeepMindGoogleDeepMind·Collected 22d ago

👀192

🔥99

View on 𝕏 ↗

Gemini 4 Argon is generally available: gemini-4-argon ships in the Gemini API and AI Studio with a 1M unified window, long decode and $2/$10 intro pricing

On Oct 13 Google made Gemini 4 Argon globally available: the stable gemini-4-argon model is live on the Gemini API paid tier and AI Studio, in Antigravity for AI Ultra, and in the Gemini app and AI Mode for Pro and Ultra subscribers. Input, thinking and output share a 1,048,576-token window, and background execution lets one response run up to 1M tokens. Intro pricing is $2 input / $10 output per million tokens through Nov 30, then $4 / $20. There is no free tier, explicit caching is unsupported, and temperature/top_p/top_k are ignored.

Gemini 4 Argon is generally available: gemini-4-argon ships in the Gemini API and AI Studio with a 1M unified window, long decode and $2/$10 intro pricing

Key Takeaways

Model ID gemini-4-argon is marked GA (Stable) in the Gemini API changelog; text/image/video/audio/PDF in, a 1,048,576-token unified window, 65,536 default synchronous output
Pricing (official): $2 input / $10 output (incl. thinking) per 1M tokens through Nov 30, 2026, then $4 / $20; implicit cache hits at 95% off ($0.10); not on the Free tier or the Google AI Pro plan
Long decode: with background: true and max_output_tokens above 65,536 the server chains 64K hops up to ~1M tokens minus input (guide)
Vendor-reported: #1 on Vals Index, 87% on ERQA, 0.7% attack success on Gray Swan indirect prompt injection across 15 adaptive attempts; internally +35% agentic code submissions in Antigravity with roughly a third fewer rollbacks
Antigravity expands to AI Pro (official @antigravity, Oct 15): Pro gets a separate weekly-only Argon quota alongside the 3.8 Flash bucket, size not published; Google case studies: Gemma 4 E2B on vLLM/A100 went from ~37,900 to 108,000+ tokens/s (2.85x); ADK cut long-session prep time 40% and cold imports 21%

Read full story

Linked Models & Agents:

⚡ Gemini 4 Argon ⚡ Gemini 4 Argon ⚡ Gemini 4 Argon 🤖 Google Antigravity 🌐 Google DeepMind 🌐 google-deepmind

#Gemini 4 Argon#Google DeepMind#Gemini API#GA#long decode#Antigravity#model launch

Hugging Face Daily Papers@HuggingFace·Collected 23d ago

👀84

🔥98

First Empirical Study on Agent Skill Evolution Reveals Concrete Rules in SKILL.md Boost Agent Correctness

In modern coding agent ecosystems (such as Claude Code, Cursor, Cline, and Antigravity), Agent Skills—specialized instruction files like SKILL.md and CLAUDE.md that dictate project architecture, commands, and rules—are continuously revised by developers alongside source code. Yet the concrete impact of these revisions on agent behavior and inference cost has remained largely unquantified. In a comprehensive empirical audit (arXiv:2610.04832), researchers analyze 2,608 first/last revision pairs across 3,159 Skills to measure the effects of revisions across 21 foundation models and four sandboxed coding agents. The study reveals that 55% of revisions alter specific rules or procedures. Adding a concrete rule raises compliance in single answers by +0.41 across open-weight models, increases required action adherence by +0.23 across sandboxed agents, and improves final task correctness by +0.10 in blind evaluations. Critically, these gains are overwhelmingly driven by rules that specify explicit CLI commands or exact file paths, whereas abstract stylistic guidance offers negligible lift. The paper also documents the performance and token trade-offs of dynamic on-demand skill loading.

Key Takeaways

First empirical study on Agent Skill evolution audits 3,159 Skills and 2,608 revisions across 21 models and 4 agents
Adding a concrete rule raises compliance by +0.41, sandbox action execution by +0.23, and final correctness by +0.10
Performance gains stem almost entirely from explicit commands and paths; dynamic on-demand loading retains 51% of efficacy

Read full story

Linked Models & Agents:

⚡ SKILL.md⚡ CLAUDE.md⚡ Open-Weight LLMs🤖 Coding-Agent 🤖 Sandbox-Agent 🤖 Claude-Code 🌐 Open Source Community 🌐 Hugging Face

#Agent Skills#SKILL.md#Coding Agents#Prompt Engineering#Developer Tools#Open Source

L

Louis Raillé@Louis-CFM·Collected 32d ago

👀146

🔥97

Coucou hits ★3146: open-source notch companion for Claude Code/Codex approvals; Linux beta ships

Open-source Louis-CFM/coucou (MIT, ★3146) parks Claude Code/Codex/Cursor/Gemini CLI/Antigravity sessions in the Mac notch (top-edge island on Windows/Linux), with in-island Allow/Deny/Always approvals, live diffs, file drop, and service pills. macOS v0.1.3 shipped 2026-10-03; Linux 0.1.1 beta is out; Windows installer is paused for a Defender false positive.

Coucou hits ★3146: open-source notch companion for Claude Code/Codex approvals; Linux beta ships

Key Takeaways

Repo Louis-CFM/coucou MIT — ★3146 / 494 forks at dig time; site louis-cfm.github.io/coucou
Watches Claude Code, Codex, Cursor, Gemini CLI, Antigravity; third-party pills via coucou_agent (AGENTS.md)
In-island Allow/Deny/Always + AskUserQuestion for Claude Code; hooks no-op if Coucou is closed (never blocks the CLI)
macOS v0.1.3 (2026-10-03); Linux linux-v0.1.1 beta; Windows installer paused (Defender FP — build from source)
No telemetry/account; secrets in OS keystores

Read full story

Linked Models & Agents:

🤖 Claude Code 🤖 Codex 🤖 Cursor 🤖 Gemini CLI 🤖 Antigravity 🤖 Coucou 🌐 Anthropic 🌐 OpenAI 🌐 Google

#Coucou#Claude code#Codex#Notch#Dynamic island#Agent companion#Macos#Linux#Open source#Hooks

Google Antigravity@Google·Collected 32d ago

👀500

🔥97

Google Antigravity lists Claude Opus/Sonnet 5.5: paid non-trial Pro + Ultra only; Claude 4.6 and GPT-OSS-120b retire Nov 2

Official Antigravity Models docs now list Claude Sonnet 5.5 (thinking) and Claude Opus 5.5 (thinking): Free/Plus/Enterprise ❌; Google AI Pro non-trial only ✅; Ultra ✅. Footnote: Claude 4.6 and GPT-OSS-120b remove on 2026-11-02. No separate changelog post—docs table is the source. No invented Antigravity SWE scores.

Google Antigravity lists Claude Opus/Sonnet 5.5: paid non-trial Pro + Ultra only; Claude 4.6 and GPT-OSS-120b retire Nov 2

Key Takeaways

Source of truth: antigravity.google/docs/models + /docs/plans — Claude 5.5 (thinking) rows are live in the table
Access: Google AI Ultra and paid non-trial Pro only; Free/Plus/Enterprise/trial Pro excluded
Retirement: Claude Sonnet/Opus 4.6 and GPT-OSS-120b removed 2026-11-02 per docs footnote
Switching: model picker under the prompt; mid-turn changes apply after the turn ends or is cancelled
Quotas: Pro/Ultra five-hour + weekly limits; optional AI Credit overages; no BYOK

Read full story

Linked Models & Agents:

⚡ Claude Opus 5.5 ⚡ Claude Sonnet 5.5 ⚡ Gemini 3.1 Pro ⚡ Gemini 3.8 Flash⚡ GPT-OSS-120b🤖 Antigravity 🤖 Claude Agent 🌐 Google 🌐 Anthropic

#Google#Antigravity#claude-opus-5.5#claude-sonnet-5.5#Model picker#Agent IDE#Google AI pro#Google AI ultra

Shengzhe@shengzheyao·Collected 33d ago

👀188

🔥95

View on 𝕏 ↗

Antigravity CLI 1.2.15 on your phone: official Android binaries run in Termux, no proot

On 2026-10-02 the Antigravity CLI author said agy 1.2.15 runs the full agent in Android Termux. The GitHub release adds prebuilt native Android binaries and drops the proot-distro requirement. Install docs still list only desktop OSes, and there is no public on-phone benchmark.

Antigravity CLI 1.2.15 on your phone: official Android binaries run in Termux, no proot

Key Takeaways

Release: Antigravity CLI 1.2.15 (ae27bff) ships prebuilt native Android binaries that run in Termux without proot-distro
This is the full local agent on the phone, not Remote Control of a desktop session; same harness as Antigravity 2.0
Denied permissions (including from subagents) are respected; a too-low AI credits balance fails immediately instead of ~2.5 minutes of retries
Install: official install.sh inside Termux, then agy; AGY_CLI_HIDE_LOGO (since 1.1.19) helps narrow screens
Caveat: install docs still list only macOS/Linux/Windows; no public Termux latency or coding score. Older community patches are not 1.2.15 results

Read full story

Linked Models & Agents:

🤖 antigravity-cli 🤖 agy 🌐 Google DeepMind 🌐 google-deepmind

#Antigravity#Antigravity CLI#Agy#Termux#Android#Google DeepMind#CLI#Agent#1.2.15