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

O
OpenAI@AICoder·
👀34
🔥80

OpenAI Codex CLI 0.166.0: keyboard transcript selection, GPT-6.1 Terra in Vertex AI and Bedrock catalogs, codex doctor network checks

OpenAI published the stable Codex CLI release rust-v0.166.0 on GitHub at 19:47 UTC on Oct 29. It adds keyboard-driven transcript selection by word, line and page with built-in search, adds GPT-6.1 Terra to the bundled, Vertex AI and Amazon Bedrock model catalogs, introduces codex queue --resume and codex doctor --network-only, and shows clearer safety-block explanations with selectable safer follow-up prompts in the TUI.

Key Takeaways

  • Model catalogs: GPT-6.1 Terra added to the bundled, Vertex AI and Amazon Bedrock catalogs (#57293)
  • Transcript: keyboard selection by word, line and page, integrated search and configurable shortcuts (#57221 to #57224)
  • New commands: codex queue --resume resumes unloaded threads after queueing a message; codex doctor --network-only checks config, connectivity and WebSocket
  • Safety UX: clearer explanations when a request is blocked, plus selectable safer follow-up prompts (#57363, #57365)
  • Fixes: approval and permission settings survive resume and fork, and reasoning-token accounting is preserved to avoid premature compaction
Read full story
Linked Models & Agents:
⚡ GPT-6.1 Terra🤖 Codex CLI🌐 OpenAI
#Codex CLI#OpenAI#GPT-6.1 Terra#Amazon Bedrock#Vertex AI#codex doctor#TUI#coding agent
O
OpenAI DevelopersOpenAIDevs·
👀219
🔥86
View on 𝕏 ↗

Codex on Windows gets a Microsoft Execution Containers (MXC) sandbox: no admin setup, no extra accounts or firewall rules, native network policy and granular file access

On Oct 9 OpenAI Developers announced a new Codex sandbox mode on Windows built on Microsoft Execution Containers (MXC), promising faster setup, stronger network enforcement and granular file access controls on compatible Windows 11 devices. Docs now list MXC as the recommended implementation, with elevated/unelevated as legacy fallbacks. It ships in Codex CLI 0.162.0, where features.prefer_mxc is off by default in the standalone CLI; the desktop app enables it via rollout.

Codex on Windows gets a Microsoft Execution Containers (MXC) sandbox: no admin setup, no extra accounts or firewall rules, native network policy and granular file access

Key Takeaways

  • Windows sandbox implementations go from 2 to 3: mxc (recommended) / elevated (preferred fallback) / unelevated (weaker network isolation)
  • MXC needs zero admin elevation, zero extra Windows accounts, zero local firewall rules; commands run as the user with per-command policy
  • Minimum Codex CLI 0.162.0; features.prefer_mxc is off by default in the standalone CLI
  • Enterprises can block MXC with windows.allow_mxc = false in requirements.toml
  • Official post: 650+ likes, 51.8K impressions within ~1.5 hours
Read full story
Linked Models & Agents:
🤖 Codex🤖 Codex CLI🌐 OpenAI🌐 Microsoft
#Codex#Windows#MXC#Microsoft Execution Containers
N
Niko1221@Niko1221·
👀307
🔥88

Strata goes viral: run 125B Qwen3.8-Flash-Next on a 12 GB gaming GPU, ~94 tok/s measured on RTX 5070

Strata, an open-source C++ inference engine, runs the 125B-parameter (6B active) Qwen3.8-Flash-Next on a 12 GB gaming GPU plus 32–64 GB RAM, exposing OpenAI, Anthropic and Responses-compatible APIs on localhost so Claude Code and Codex CLI can use it. The repo passed 10k GitHub stars and hit the Hacker News front page (507 points).

Strata goes viral: run 125B Qwen3.8-Flash-Next on a 12 GB gaming GPU, ~94 tok/s measured on RTX 5070

Key Takeaways

  • Scale: Qwen3.8-Flash-Next is 125B total / 6B active (512 experts, 10 routed + 1 shared), 262K native context
  • Measured: RTX 5070 12 GB + 64 GB RAM, Q2_0 decodes ~94 tok/s and prefills a 32K prompt at ~2,650 tok/s; RX 9070 XT ~60 tok/s
  • Requirements: 12 GB VRAM and 32 GB RAM minimum, ~70 GB download; the Coder pack drops half the experts and keeps ~91% of SWE-bench Verified per its authors
  • Integration: localhost OpenAI, Anthropic /v1/messages and Responses endpoints plus an MCP server
  • Traction: ~10.7k stars, 946 forks, MIT license, v0.1.39 released Oct 4
Read full story
Linked Models & Agents:
⚡ Qwen3.8-Flash-Next🤖 Claude Code🤖 Codex CLI🌐 Alibaba Qwen🌐 NVIDIA🌐 AMD
#Local LLM#Inference#Moe#Qwen#Consumer GPU#Open source
D
DigitalOcean@digitalocean·
👀58
🔥95

DigitalOcean Agent Droplets: harness + inference + 16k tools in one monthly plan from $50/$200

On 2026-10-01 DigitalOcean launched Agent Droplets for Managed Agents (public preview): Pro $50/mo (15% off) and Team $200/mo (20% off) bundling Harness Runtime microVMs, DO-hosted open-model inference (Kimi K3, GLM 5.3), session storage, and Action Gateway (16,000+ tools). Works with Claude Code, Codex CLI, OpenCode. Paired with prepaid Inference and Agents Balance.

DigitalOcean Agent Droplets: harness + inference + 16k tools in one monthly plan from $50/$200

Key Takeaways

Read full story
Linked Models & Agents:
⚡ GLM-5.3⚡ Kimi K3🤖 Claude Code (Anthropic)🤖 openai-codex🤖 opencode🌐 digitalocean🌐 Anthropic🌐 OpenAI🌐 alibaba
#DigitalOcean#Agent Droplets#Managed Agents#Harness Runtime#Action Gateway#Claude Code#Codex#OpenCode#GLM 5.3#Pricing
ADSponsored
O
OpenAI@openai·
👀86
🔥88

OpenAI Codex 0.159.2: suppress Windows console window flashing for background/sandbox processes

OpenAI Codex CLI shipped rust-v0.159.2 (npm @openai/[email protected]): backport #49385 suppresses Windows console window flashing when launching background processes and sandboxed commands (tracks #48074). Diff vs v0.159.1: ~2 commits / 47 files. Default model remains GPT-6.1 Sol from 0.159.1.

OpenAI Codex 0.159.2: suppress Windows console window flashing for background/sandbox processes

Key Takeaways

  • Release rust-v0.159.2 / npm 0.159.2
  • Windows: suppress console flashes for background + sandboxed commands (#49385 / #48074)
  • ~2 commits / 47 files vs v0.159.1
  • Default model still GPT-6.1 Sol from 0.159.1
  • Upgrade: npm i -g @openai/[email protected]; smoke-test on Windows sandbox hosts
Read full story
Linked Models & Agents:
⚡ GPT-6.1 Sol⚡ GPT-6.1 Sol🤖 Codex🌐 OpenAI
#OpenAI#Codex#Windows#CLI#Coding agent#Bugfix#Release
O
OpenAIopenai·
👀108
🔥96

OpenAI Codex 0.159.1: GPT-6.1 Sol becomes default; Bedrock Mantle & Runtime catalogs updated

OpenAI Codex CLI shipped rust-v0.159.1 on 2026-09-29 (npm @openai/[email protected]): GPT-6.1 Sol is now the default in the bundled catalog and Amazon Bedrock Mantle/Runtime catalogs (API id gpt-6.1-sol). Official pricing $2/$10 per 1M tokens (cached input $0.10), 1.05M context, 128k max output. ~3 commits / 29 files vs v0.159.0.

OpenAI Codex 0.159.1: GPT-6.1 Sol becomes default; Bedrock Mantle & Runtime catalogs updated

Key Takeaways

Read full story
Linked Models & Agents:
⚡ GPT-6.1 Sol⚡ GPT-6.1 Sol🤖 Codex🌐 OpenAI🌐 Amazon Bedrock
#OpenAI#Codex#gpt-6.1-sol#CLI#Coding agent#Bedrock#Release
O
OpenAI@openai·
👀85
🔥94

OpenAI Codex 0.159.0: opt-in instant_interrupt steering; warning dismiss; richer Mermaid & thread pagination

OpenAI Codex shipped rust-v0.159.0 on 2026-09-29 (npm @openai/[email protected]): opt-in instant_interrupt steers mid-response or long code-mode calls; compact welcome/headers; warnings viewer dismisses reviewed items on close (k to keep); scroll transcript while reviewing a plan; richer native Mermaid; app-server can paginate thread history from an item anchor. ~89 commits / 300 files vs v0.158.0. Windows suppresses stray consoles for MCP/code-mode; .aws protected under writable roots; macOS sandbox TLS/proxy fixes.

OpenAI Codex 0.159.0: opt-in instant_interrupt steering; warning dismiss; richer Mermaid & thread pagination

Key Takeaways

  • Release rust-v0.159.0 on 2026-09-29; ~89 commits / 300 files vs v0.158.0
  • Opt-in instant_interrupt steers mid-response / long code-mode (#48135/#48141)
  • Warnings dismiss on close (k to keep); scroll while reviewing plans; richer Mermaid
  • App-server paginates thread history from an item anchor (#48151)
  • Install: npm i -g @openai/[email protected]; removed tui.prompt_suggestions and bundled plugin-creator skill
Read full story
Linked Models & Agents:
🤖 Codex🤖 code-mode🌐 OpenAI
#OpenAI#Codex#CLI#MCP#Instant interrupt#Release
O
OpenAI@OpenAI·
👀103
🔥94

Codex CLI 0.157.0: GPT-6 Sol/Luna (incl. Bedrock), fullscreen transcript + background daemon by default

OpenAI Codex CLI rust-v0.157.0 (2026-09-25) adds GPT-6 Sol/Luna (incl. Amazon Bedrock), enables fullscreen transcripts and auto background-server startup by default, adds an f shortcut to fork locked conversations, and enables /import in remote and local daemon sessions.

Codex CLI 0.157.0: GPT-6 Sol/Luna (incl. Bedrock), fullscreen transcript + background daemon by default

Key Takeaways

  • GPT-6 Sol/Luna in catalog + Amazon Bedrock (#47332/#47347)
  • Fullscreen transcript + auto background-server default (#47178/#47179/#47318)
  • f forks locked conversations; /import in remote/daemon sessions (#47185/#47317)
  • Proxy + network policy hardening for realtime/search (#47101/#47389)
  • Upgrade: npm i -g @openai/[email protected]
Read full story
Linked Models & Agents:
⚡ GPT-6 Sol⚡ GPT-6 Luna🤖 Codex CLI🌐 OpenAI🌐 Amazon Bedrock
#Codex#GPT-6#Sol#Luna#Bedrock#TUI#Daemon
O
OpenAI@OpenAIDevs·
👀105
🔥90

Codex CLI 0.156: optional /tui fullscreen, voice on by default, /usage dashboard; 0.156.1 adds GPT-6 Sol/Luna

OpenAI shipped Codex CLI rust-v0.156.0 and hotfix 0.156.1 on 2026-09-22/23 (@openai/codex). 0.156.0 adds optional /tui fullscreen, voice default-on, /usage, worktrees on by default, themes/Mermaid, plus sandbox fixes. 0.156.1 adds GPT-6 Sol/Luna to the picker and recommends Luna on rate-limit switches.

Key Takeaways

  • Install @openai/[email protected] (0.156.0, 0.156.1)
  • /tui fullscreen; voice default-on (F8); /usage dashboard
  • Worktrees enabled by default from the agent command center
  • Sandbox isolation fixes for Windows inbound, privileged sockets, macOS handles
  • 0.156.1 adds GPT-6 Sol/Luna; rate-limit prompt recommends Luna
Read full story
Linked Models & Agents:
⚡ GPT-6 Sol⚡ GPT-6 Luna🤖 Codex🌐 OpenAI
#Codex CLI#OpenAI#TUI#Voice#GPT-6#Worktree
D
Dan Kornas@DanKornas·
👀42
🔥89
View on 𝕏 ↗

Pond open-sources cross-client storage and search for coding-agent sessions

@DanKornas introduced tenequm/pond, an open-source storage and search layer for AI-agent sessions. It ingests history from clients such as Claude Code, Codex CLI, and Hermes Agent, stores it locally or in user-owned S3, and exposes BM25 search, read-only SQL, and MCP access for retrieving and restoring prior decisions, fixes, and dead ends. The repository had about 69 GitHub stars at verification and uses Apache-2.0.

Key Takeaways

  • Ingests session history across Claude Code, Codex CLI, Hermes Agent, and other clients into local or user-owned S3 storage.
  • Provides BM25 full-text search and read-only SQL for retrieving prior decisions, fixes, and dead ends.
  • Exposes MCP access and session restoration; tenequm/pond had about 69 stars at verification under Apache-2.0.
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🤖 Cursor Composer (Agent Mode)🤖 Aider
#Pond#AI agent#session memory#MCP#Claude Code#Codex CLI#open source
ADSponsored
C
Codex Changelog@Codex_Changelog·
👀66
🔥90
View on 𝕏 ↗

Codex CLI 0.155.0 adds experimental /voice, live reasoning summaries, and Touch ID for MCP

Codex CLI 0.155.0 is out with experimental /voice including live transcripts and mic controls, live reasoning summaries and turn timestamps in the status row, and Touch ID approval for MCP requests on Mac. The release is tagged rust-v0.155.0 on GitHub.

Key Takeaways

  • Experimental /voice adds live transcripts and mic controls after enabling /experimental.
  • The status row now shows live reasoning summaries and turn timestamps for long runs.
  • MCP requests on Mac can be approved with Touch ID, reducing friction for sensitive tool calls.
Read full story
Linked Models & Agents:
🤖 codex🌐 OpenAI
#Codex CLI#0.155.0#Voice#MCP#Touch ID#OpenAI
A
Arena@arena·
👀66
🔥94
View on 𝕏 ↗

Arena: Native Coding Harness Matters Less Than Assumed Across 21 Model Pairs

LMSYS Arena published a coding-agents harness study comparing Claude Code, Codex CLI, and Pi. Across 21 rigorously tested model-harness pairs, the harness tax mattered far less than many assume—model quality still dominated. Details are on the Arena blog.

Key Takeaways

  • Compared Claude Code, Codex CLI, and Pi as native coding harnesses for agents
  • 21 model-harness pairs showed a smaller harness tax than many assume
  • Model quality still dominated; more Arena findings are forthcoming
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🤖 codex🌐 arena🌐 Anthropic🌐 OpenAI
#Arena#Claude Code#Codex CLI#Pi#coding agents#Harness
R
RRweb3@RRweb3·
👀49
🔥88
View on 𝕏 ↗

Google ships free Cloud Developer Plugin for Claude Code, Codex CLI, and Antigravity

Reports say Google released a free Google Cloud Developer Plugin so AI coding agents can use official cloud knowledge and tools (project setup, auth, gcloud, docs) instead of guessing GCP workflows. Claude Code install: claude plugin marketplace add google/skills, then claude plugin install google-cloud-developer@google-plugins; Codex CLI and Antigravity have their own install paths. The plugin is free; normal GCP/API usage still bills separately.

Key Takeaways

  • Free Google Cloud Developer Plugin targets Claude Code, Codex CLI, and Antigravity.
  • Grounds agents in official cloud knowledge/tools instead of guessing GCP flows.
  • Claude Code: marketplace add google/skills then install google-cloud-developer@google-plugins.
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🤖 openai-codex🤖 Google Antigravity (AGY)🌐 Google DeepMind
#Google Cloud#Developer Plugin#Claude Code#Codex CLI#Antigravity#Gcloud#Skills#Free
j
janak@janaksunil·
👀39
🔥96
View on 𝕏 ↗

Specific launches Real-SWE: private production codebases; Fable+Claude Code tops at 38.8%

Specific Labs (@janaksunil) launched Real-SWE, evaluating coding agents on private, out-of-distribution production codebases from real companies (200K+ user apps, fintech statement pipelines, enterprise sales tools, and more). On the public board (8-run averages) Claude Fable 5.1 + Claude Code leads at 38.8%, GPT-6 Astra + Codex CLI at 33.8%, and Gemini 3.8 Flash + Gemini CLI at 31.2% — none clear 40%. Site: realswe.withspecific.com.

Key Takeaways

  • Tasks come from real private company codebases — billing, permissions, customer data — not public contest repos.
  • 8-run averages: Fable 5.1 + Claude Code 38.8%, Astra + Codex CLI 33.8%, Gemini 3.8 Flash + Gemini CLI 31.2%.
  • Built for the systems companies would actually deploy agents into; board at realswe.withspecific.com.
Read full story
Linked Models & Agents:
🤖 Claude Code (Anthropic)🤖 openai-codex🤖 cursor
#Real-SWE#Specific Labs#Claude Code#Codex CLI#Gemini CLI#Fable 5.1#GPT-6 Astra#Benchmark
t
tea@iasg1004·
👀64
🔥88
View on 𝕏 ↗

Codex CLI 0.154.0: experimental managed Git worktrees keep the main tree clean

npm latest @openai/codex is 0.154.0. After codex features enable worktrees, --worktree / /worktree spins a managed Git worktree from committed HEAD (detached) and binds the session to it, so uncommitted edits, .env, and node_modules stay out of the agent checkout. codex resume --worktree and codex review --worktree are rejected. Aimed at parallel agents that otherwise fight one dirty working tree.

Key Takeaways

  • 0.154.0 adds experimental managed Git worktrees after enabling the feature flag.
  • Sessions bind to a detached checkout so dirty files and local deps stay out.
  • resume/review reject --worktree; npm latest confirms 0.154.0.
Read full story
Linked Models & Agents:
🤖 codex🌐 OpenAI
#Codex#CLI#0.154.0#Worktree#Git#OpenAI#Tooling