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

C
Cursor@cursor_ai·
👀122
🔥85
View on 𝕏 ↗

Cursor launches Agent SDK: agents as code with Markdown prompts, TypeScript tools, built-in evals, and hosted or self-run deployment

On Oct 26 Cursor announced that its Agent SDK is generally available. An agent's system prompt is written in Markdown and its tools in TypeScript; agents can be deployed on Cursor's hosted infrastructure or run on your own machines, and built-in evals measure every change. Cursor's docs say it uses the same Cursor SDK harness that powers Bugbot, Security Review, Approval Bot and Rollouts, can be triggered from source-control events, issue trackers, Slack or schedules, and is managed under Deployed Agents after deployment. Cursor has not published pricing or benchmarks.

Cursor launches Agent SDK: agents as code with Markdown prompts, TypeScript tools, built-in evals, and hosted or self-run deployment

Key Takeaways

  • Same harness: Cursor's docs say Agent SDK runs on the harness behind four of its own agents: Bugbot, Security Review, Approval Bot and Rollouts
  • Project layout: bot/instructions.md is the required always-on system prompt, each bot/tools/*.ts file is one typed tool, with folders for skills, MCP connections, subagents, channels, hooks and schedules, and evals live in evals/*.eval.ts
  • Triggers and deployment: runs can be triggered from source control, issue trackers, Slack, webhooks or schedules; deploy on Cursor-managed hosting or self-host, then manage under Deployed Agents
  • CLI: agent-sdk validate, run and eval check the project, run a real turn and run evals; Cursor says only run and eval need a Cursor credential
  • Cursor has not published pricing or benchmarks
Read full story
Linked Models & Agents:
🤖 Cursor🤖 Bugbot🌐 Cursor
#Cursor#Agent SDK#agents as code#Evals#TypeScript
M
Matt Pocock@mattpocockuk·
👀57
🔥81
View on 𝕏 ↗

X discussion: Matt Pocock sketches the ideal "language for agents" (Rust speed, Go-sized design space, strictest verification) and names Bend; Chris Lattner replies with Mojo

At 17:23 UTC on 2026-10-25, TypeScript educator Matt Pocock (@mattpocockuk, author of Total TypeScript and AI Hero) posted (post) that the next great "language for agents" should be as fast as Rust, have as little design space as Go, and have the strictest type/verification system ever written, calling Bend "an interesting first effort". When we pulled it, the post had about 3,130 likes, 84 reposts, 264 replies, 786 bookmarks and 220K views, and it reached X's trending stories. Mojo creator Chris Lattner replied (reply) recommending Mojo and suggesting "can target all hardware" be added to the list. This is an opinion debate, not a verified conclusion.

Key Takeaways

  • Main post: post, published 17:23 UTC on 10-25, with about 3,130 likes, 84 reposts, 264 replies, 786 bookmarks and 220K views when we pulled it
  • Three criteria: Rust-level speed, a Go-sized design space (few ways to write the same thing), and the strictest type/verification system ever written, so the compiler rather than a human catches agent mistakes
  • Chris Lattner replied recommending Mojo, citing advanced type features such as linear types and symbolic constraints, and suggested adding "can target all hardware" (reply, about 40 likes when pulled)
  • Bend creator Victor Taelin (@VictorTaelin) also joined the thread, saying Bend blocking an agent from breaking an app is "working as intended"
  • No benchmarks or controlled comparisons were shared; whether Bend or Mojo suits agent coding remains personal opinion
Read full story
Linked Models & Agents:
#Bend#Mojo#Matt Pocock
C
ClaudeDevsClaudeDevs·
👀68
🔥86
View on 𝕏 ↗

Claude API ships version 2026-10-21, its first since 2023: sampling parameters removed, new major SDKs across languages

On Oct 21 Anthropic released Claude API version 2026-10-21, its first official version since 2023. It removes the temperature, top_p and top_k sampling parameters and drops old Admin API field names, while new SDK majors (Python 2.0, TypeScript 1.0, Go 2.0, Java 3.0 and more) default to it. Version 2023-06-01 is not deprecated.

Key Takeaways

  • Version: 2026-10-21 is the Claude API's first official version since 2023; 2023-06-01 is not deprecated and more frequent versions are planned
  • Breaking: sending temperature, top_p or top_k returns a 400 on every model; Claude 4.7+ models behave as before
  • SDKs: Python 2.0.0, TypeScript 1.0.0, Go 2.0.0 (/v2 path), Java 3.0.0, C# 13.0.0, Ruby 2.0.0, PHP 1.0.0, ant CLI 2.0.0
  • Auth: SDKs send the API key as Authorization: Bearer and hold 1 credential per client; SDK license moves to Apache 2.0
  • Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry, Google Cloud; Bedrock only for Claude 4.7+, see the migration guide
Read full story
Linked Models & Agents:
⚡ Claude Opus 5.5⚡ Claude Sonnet 4.6🤖 Claude API🤖 ant CLI🌐 Anthropic
#Claude API#API versioning#SDK#breaking changes
P
Prime Intellect@PrimeIntellect·
👀111
🔥86
View on 𝕏 ↗

Prime Intellect's Prime Agent used a 2,209-agent swarm to rewrite itself in Rust: time-to-type 738ms→56ms, 80%+ less memory

On Oct 9 Prime Intellect shipped a Rust rewrite of Prime Agent, its open-source coding agent harness. A root orchestrator ran 2,209 sub-agents across 10,000+ Prime Sandboxes and ~228.7B GLM-5.3 tokens over two weeks, with differential TUI, harness and protocol parity tests gating every merge. Vendor-measured cold time-to-type dropped from 737.8ms to 55.8ms and post-startup memory from 607MB to 106MB; Windows (beta) and Homebrew installs were added.

Prime Intellect's Prime Agent used a 2,209-agent swarm to rewrite itself in Rust: time-to-type 738ms→56ms, 80%+ less memory

Key Takeaways

  • Scale: 2,209 agents, 16,758 agent-to-agent messages, 228.70B tokens (192.99B/1,981 agents for the port, 35.70B/228 for perf hillclimbing) across 10,000+ Prime Sandboxes
  • Vendor-measured: cold time-to-type 737.8ms→55.8ms (13.22x), first paint 722.8ms→23.6ms, post-startup RSS 607.4MB→106.0MB, install 172.1MB→59.6MB
  • Each task ran a Planner→Implementer→adversarial Reviewer (different model)→Verifier state machine; failures loop back to the implementer
  • A 3-day target-free hillclimb loop logged 144+ experiment/audit records and merged 69+ performance changes
  • Codebase now 9 crates, largest file ~2,500 lines (was ~15,000); native Windows (beta) and Homebrew installs, still open source
Read full story
Linked Models & Agents:
⚡ GLM-5.3🤖 Prime Agent🤖 Claude Code🤖 Codex CLI🌐 Prime Intellect
#Prime Agent#Rust#Agent Swarm
ADSponsored
T
Theo - t3.gg@theo·
👀238
🔥87
View on 𝕏 ↗

Theo open-sources tsc-rs: Opus 5.5 ported the TypeScript 7 compiler to Rust in two weeks for ~$24K, type-checking ~1.6x faster than the Go version

Theo (T3) open-sourced ts-rust (npm: tsc-rs), a Rust port of Microsoft's Go-native TypeScript compiler, checker and language server. Months of GPT-5.6 Sol / GPT 6 Astra runs cost over $400K in API-priced tokens and stalled near 84% compatibility; Claude Opus 5.5 restarted from scratch, reached a working v0 in 10 hours and finished in two weeks for about $24,047. All 181,711 ported Go tests pass, it type-checks 1.61x faster than tsc 7 (geometric mean over six open-source apps), ships Effect diagnostics built in and has a WASM build.

Theo open-sources tsc-rs: Opus 5.5 ported the TypeScript 7 compiler to Rust in two weeks for ~$24K, type-checking ~1.6x faster than the Go version

Key Takeaways

  • Cost: GPT-5.6 Sol / GPT 6 Astra burned $400K+ and stalled near 84% compat; Opus 5.5 finished in 2 weeks for ~$24,047 (README)
  • Correctness: all 181,711 ported Go tests pass; TanStack Query core and Hono diagnostics match Go exactly
  • Speed: geometric mean 11.4x over tsc 6 and 1.61x over tsc 7 on six apps; VS Code (3.75M lines) 4.20s vs 6.84s for tsc 7; bun check is still fastest (20.9x)
  • T3 Code: 7.25s vs 16.10s for tsc 7 without Effect (2.22x); 11.13s vs 21.07s with Effect diagnostics (1.89x)
  • Early release: Linux x64 and macOS arm64 only; known monorepo TS6059 and tsc -b stale-output issues
Read full story
Linked Models & Agents:
⚡ Claude Opus 5.5⚡ GPT-6 Astra⚡ GPT-5.6 Sol🤖 Claude Code🤖 Codex🌐 Anthropic🌐 OpenAI🌐 Microsoft🌐 T3
#TypeScript#Rust#Claude Opus 5.5
C
ClaudeDevs@ClaudeDevs·
👀82
🔥88
View on 𝕏 ↗

Claude's Python and TypeScript SDKs now ship built-in computer-use and browser-use toolsets: the SDK runs the agent loop, you only write the driver

Anthropic's Python SDK 1.12.0 and TypeScript SDK 0.132.0 add computer_toolset_20260801 and browser_toolset_20260801: a single tools[] entry declares a whole family of desktop or browser actions, the SDK tool_runner executes them in order and stops at the first failure, and url_policy, file_policy and confirm hooks run before each call. Developers no longer hand-write the loop that maps clicks and keystrokes to commands; they subclass an abstract toolset and plug in their own VNC, DevTools or hosted-browser backend.

Claude's Python and TypeScript SDKs now ship built-in computer-use and browser-use toolsets: the SDK runs the agent loop, you only write the driver

Key Takeaways

  • Versions: Python anthropic 1.12.0 and TypeScript SDK 0.132.0 (2026-10-07) add typed computer and browser toolset calls
  • The computer toolset covers 17 actions (screenshot, left_click, type, scroll, zoom...); unimplemented ones are sent as enabled: false (docs)
  • The browser toolset adds navigate, tabs, read_page, read_network, form_input, file_upload and more, with url_policy checked on every navigate (docs)
  • Official 7-step safety checklist: URL policy, request interception, container egress rules, file policy, confirm gates, per-session isolation, treat page content as untrusted
  • ClaudeDevs announcement drew 3,500+ likes and 248K views; no new benchmark numbers were published
Read full story
Linked Models & Agents:
⚡ Claude Sonnet 5⚡ Claude Haiku 5.5🤖 Claude Computer Use🌐 Anthropic
#Anthropic#Computer Use#Browser Use#SDK#Agent#Security
酥
酥酥@NFT_Chen·
👀74
🔥95
View on 𝕏 ↗

SpaceXAI official TypeScript SDK is public: one package for Grok text, voice, image, video, and hosted tools

On 2026-10-02 xAI published the official TypeScript SDK @xai-official/sdk (repo xai-org/xai-sdk-ts, Apache-2.0). The same day, 0.2.0 renamed the client to SpaceXAI; npm latest at fetch was 0.2.1. One ESM package covers Grok text, voice, image and video, plus hosted web search, X search, code execution, and remote MCP. Zero runtime dependencies, Node 22.13+, and browser use blocked by default. No public benchmark.

SpaceXAI official TypeScript SDK is public: one package for Grok text, voice, image, video, and hosted tools

Key Takeaways

  • Package: @xai-official/sdk in xai-org/xai-sdk-ts, Apache-2.0, zero runtime deps. npm latest at fetch was 0.2.1 (2026-10-02 22:18 UTC); the post cited 0.2.0
  • 0.2.0 breaking rename: client class xAI to SpaceXAI (changelog). 0.2.1 adds toJson(schema), streaming partial JSON, and retryBeforeOutput
  • Node.js 22.13+, ESM only; browser and Worker use blocked by default. Hosted tools include web search, X search, code execution, and remote MCP; functions and shell run locally
  • No public SDK latency or coding score. About 27 GitHub stars and 312 npm weekly downloads at fetch time. Sample model grok-4.7 is not a benchmark
  • Not the same package as Vercel @ai-sdk/xai. Keep the API key on the server. Interfaces may change before 1.0; outside PRs are not accepted yet
Read full story
Linked Models & Agents:
⚡ Grok 4.7⚡ grok-imagine-image-2.0⚡ grok-imagine-video-1.5🌐 xAI🌐 spacex
#SpaceXAI#Grok#TypeScript#xAI#SDK#@xai-official/sdk#grok-4.7
A
Anthropic@AnthropicAI·
👀302
🔥94

Claude Code 2.1.287: Mods in-process extensions; built-in You should know side agent; 1M context default on gateways

Anthropic shipped Claude Code 2.1.287 on 2026-10-01 (npm @anthropic-ai/[email protected]): Claude Mods let plugins run in-process JS/TS hooks that rewrite tool calls and UI; opt-in built-in You should know side agent; MCP URL elicitation; Opus 4.7+/Fable default to 1M context on Bedrock/Vertex/Foundry/apps gateway. Agent SDK TS 0.3.287 parity.

Claude Code 2.1.287: Mods in-process extensions; built-in You should know side agent; 1M context default on gateways

Key Takeaways

  • Release v2.1.287; npm 2.1.287; GitHub ~2026-10-01T18:00:22Z
  • Mods: in-process hooks for UI + tool.call rewrite; ≥2.1.287; docs https://code.claude.com/docs/en/plugins/mods/overview
  • You should know: /plugin enable cc-plugin-you-should-know@builtin (first-party + telemetry); off by default
  • 1M context default for Opus 4.7+/Fable on Bedrock/Vertex/Foundry/apps gateway; disable via CLAUDE_CODE_DISABLE_1M_CONTEXT=1
  • Agent SDK TS 0.3.287; MCP URL elicitation / bareElicitationCapability
Read full story
Linked Models & Agents:
⚡ Claude Opus 5.5⚡ Claude Sonnet 5.5⚡ Claude Fable 5.1🤖 Claude Code (Anthropic)🌐 Anthropic
#Claude Code#Mods#You should know#Plugins#MCP elicitation#1M context#Agent SDK#2.1.287
A
Anthropic@anthropics·
👀53
🔥88

Anthropic TS SDK 0.131 / Python 1.11: Admin list spend limits; client deprecates Sonnet 4.5

Hours after 0.130/1.10 Admin GA work, Anthropic shipped @anthropic-ai/[email protected] and Python 1.11.0 at 2026-09-30T22:58Z: Admin API gains a list spend limits endpoint; both clients deprecate Sonnet 4.5 toward newer aliases (Sonnet 5.5 line).

Anthropic TS SDK 0.131 / Python 1.11: Admin list spend limits; client deprecates Sonnet 4.5

Key Takeaways

  • TS sdk-v0.131.0 at 2026-09-30T22:58:20Z; Python v1.11.0 at 22:58:09Z
  • Admin API: list spend limits endpoint (compare)
  • Clients deprecate Sonnet 4.5; prefer Sonnet 5.5 aliases for new work
  • Install: npm i @anthropic-ai/[email protected] / pip install anthropic==1.11.0; Admin docs linked above
  • No public SWE-bench; enterprise quota listing + model alias hygiene
Read full story
Linked Models & Agents:
⚡ Claude Sonnet 5.5⚡ Claude Sonnet 4.5🤖 Claude Code (Anthropic)🤖 managed-agents🌐 Anthropic
#Anthropic#SDK#Admin API#Spend limits#sonnet-4.5#Deprecation#Release
A
Anthropic@anthropics·
👀46
🔥92

Claude Code 2.1.286: stacked permission counts; resume keeps parallel-tool turns; secret redaction & model-fallback hardening

Anthropic shipped Claude Code 2.1.286 on 2026-09-30 (npm @anthropic-ai/[email protected]): permission prompts show stacked counts like "2 of 5"; --resume/--continue no longer drop turns after parallel tool-call crashes; broader secret/Bearer/URL-password redaction; one same-tier prior-model retry when the API refuses the default/alias; Remote Control disconnects when org policy disables it; Agent SDK TS 0.3.286 / Python 0.2.163 parity.

Claude Code 2.1.286: stacked permission counts; resume keeps parallel-tool turns; secret redaction & model-fallback hardening

Key Takeaways

  • Release v2.1.286; npm ~2026-09-30T17:14:38Z
  • Stacked permission prompts show counts like "2 of 5"; fullscreen "N more" rows are mouse-clickable
  • --resume/--continue keep turns after parallel tool-call crashes; non-text tool/hook returns no longer 400
  • Secret redaction hardened for Bearer/Basic, URL passwords, ZWSP key names; /feedback zip JSON fixed
  • Agent SDK TS 0.3.286 / Python 0.2.163 parity; docs https://docs.claude.com/en/docs/claude-code/overview
Read full story
Linked Models & Agents:
⚡ Claude Sonnet 5.5🤖 Claude Code (Anthropic)🌐 Anthropic
#Claude code#Anthropic#Permissions#Resume#Redaction#MCP#Agent SDK#Tooling#Release
ADSponsored
A
Anthropic@anthropics·
👀49
🔥93

Anthropic TS SDK 0.130 / Python 1.10: Admin analytics & plugin marketplaces; Organization API GA; MCP tunnels beta

Anthropic shipped @anthropic-ai/[email protected] and Python anthropic==1.10.0 on 2026-09-30: Admin API gains enterprise analytics, spend limits, RBAC groups/roles, Plugins/Plugin Marketplaces, and per-user usage/cost reports; Organization API endpoints go GA; MCP tunnels beta returns read-only transport plus one-time relay token on create; Managed Agents add refusal stop reason and repository error types.

Anthropic TS SDK 0.130 / Python 1.10: Admin analytics & plugin marketplaces; Organization API GA; MCP tunnels beta

Key Takeaways

  • Releases: TS sdk-v0.130.0 at 2026-09-30T18:29:28Z; Python v1.10.0 at 2026-09-30T18:28:45Z
  • Admin API: analytics, spend limits, RBAC, Plugins/Marketplaces, per-user usage/cost; compare
  • Organization API endpoints now GA; MCP tunnels beta adds read-only transport + one-time relay token
  • Managed Agents: refusal stop reason/stop_details on idle; repository error types
  • Install: npm i @anthropic-ai/[email protected] / pip install anthropic==1.10.0; docs https://docs.anthropic.com/en/api/admin-api
Read full story
Linked Models & Agents:
⚡ Claude Sonnet 5.5⚡ Claude Opus🤖 Claude Code (Anthropic)🤖 managed-agents🌐 Anthropic
#Anthropic#SDK#Admin API#Organization API#MCP tunnels#Rbac#Plugins#Enterprise#Release
A
Anthropicanthropics·
👀49
🔥94

Anthropic TypeScript SDK 0.129.0: claude-sonnet-5-5, between_tools thinking, start tool calls while the reply streams

Anthropic shipped @anthropic-ai/[email protected] on 2026-09-28 (36 commits ahead of 0.128.0): claude-sonnet-5-5, between_tools thinking, cache diagnostics GA, Managed Agents event type filters, ClientToolUnion, and optionally starting tool calls while the reply streams—plus streaming tokenizer/partial tool-input fixes. Mirrors the Python 1.9.0 surface for TS agents.

Anthropic TypeScript SDK 0.129.0: claude-sonnet-5-5, between_tools thinking, start tool calls while the reply streams

Key Takeaways

Read full story
Linked Models & Agents:
⚡ Claude Sonnet 5.5⚡ Claude Sonnet 5.5🤖 Managed Agents🤖 tool runner🌐 Anthropic
#Anthropic#Typescript#SDK#sonnet-5.5#Between tools#Streaming#MCP#Release#Coding agent
O
OpenAI@openai·
👀54
🔥94

OpenAI Node 7.25.0: Computer Use on beta.agents; 7.24 adds GPT-6.1 Sol + Agents credential/session options

Official TypeScript SDK [email protected] (v7.25.0, 2026-09-29) adds Computer Use to beta.agents (#2837), mirroring Python 3.22.0. Prior v7.24.0 shipped Agents credential/session options (#2812), the gpt-6.1-sol model id (#2836), Responses Cyber access, Realtime Translation client secrets, and a dedicated Node translation WebSocket. 35 commits ahead of v7.23.0.

OpenAI Node 7.25.0: Computer Use on beta.agents; 7.24 adds GPT-6.1 Sol + Agents credential/session options

Key Takeaways

  • Releases v7.24.0 → v7.25.0; npm [email protected]; 35 commits ahead of v7.23.0
  • Computer Use on beta.agents via #2837
  • gpt-6.1-sol id (#2836); Agents credential/session options (#2812)
  • Realtime Translation client secret (#2819) + Node translation WebSocket (#2818)
  • Upgrade: npm i [email protected]; docs: platform.openai.com agents + API reference
Read full story
Linked Models & Agents:
⚡ GPT-6.1 Sol⚡ GPT-6.1 Sol🤖 OpenAI Agents🤖 beta.agents🤖 Computer Use🌐 OpenAI
#Openai node#Typescript#Computer use#Agents#gpt-6.1-sol#Realtime#SDK#Release
Y
Yusuke Wada@yusukebe·
👀91
🔥94
View on 𝕏 ↗

Cloudflare launches agentic CLI `cf`: 3000+ API ops from OpenAPI, JSON-default + cloudflare.config.ts

Hono creator @yusukebe amplified Cloudflare’s launch of cf (npm i -g cf): Forge generates 3000+ CLI ops from OpenAPI (vs Wrangler’s ~280), JSON-default output, cf cli search, TypeScript cloudflare.config.ts, and Vite-default local dev. Open beta [email protected].

Cloudflare launches agentic CLI `cf`: 3000+ API ops from OpenAPI, JSON-default + cloudflare.config.ts

Key Takeaways

  • Blog: Introducing cf (2026-09-28) — agents were 48% of Wrangler use last week; surface expands ~280 → 3000+ ops
  • Install: npm i -g cf (1.0.0-beta.5); key cmds cf deploy / cf migrate / cf init / cf cli search
  • Config: TypeScript cloudflare.config.ts with defineConfig / bindings / triggers; Vite-default local DX
  • Pipeline: Forge (Apache 2.0, cloudflare/forge); CLI at cloudflare/cf
  • Migration: final Wrangler major will point to cf, then 18 months maintenance; no model SWE-Bench numbers for this CLI
Read full story
Linked Models & Agents:
🤖 cf CLI🌐 Cloudflare
#Cloudflare#cf CLI#Wrangler#Forge#Workers#Vite#OpenAPI#agentic CLI#cloudflare.config.ts
M
Model Context Protocol@modelcontextprotocol·
👀67
🔥92

MCP TypeScript SDK 2.2.0: M2M OAuth expectedIssuer, auto-paging list*, CJS jose types + Client.listen hang fixes

MCP’s TypeScript monorepo shipped v2.2.0 on 2026-09-28: client/server/core/server-legacy/codemod aligned at 2.2.0. M2M OAuth providers should pass expectedIssuer; fetchToken() throws AuthorizationServerMismatchError on issuer mismatch. Cursor-less listTools/listPrompts/listResources/listResourceTemplates now follow nextCursor (capped by listMaxPages). Fixes the 2.1.0 CJS jose types regression and Client.listen() unhandled rejection / send hang.

MCP TypeScript SDK 2.2.0: M2M OAuth expectedIssuer, auto-paging list*, CJS jose types + Client.listen hang fixes

Key Takeaways

  • Shipped v2.2.0 — client/server/core/server-legacy/codemod aligned; node/express/hono/fastify unchanged
  • M2M OAuth: pass expectedIssuer; fetchToken throws AuthorizationServerMismatchError on mismatch
  • list* without cursor auto-follows nextCursor (listMaxPages cap)
  • Fixes CJS jose types regression and Client.listen() rejection/hang
  • Install: npm i @modelcontextprotocol/[email protected]
Read full story
Linked Models & Agents:
🤖 MCP-Client🤖 MCP-Server🌐 modelcontextprotocol
#MCP#TypeScript#OAuth#DPoP#listTools#Agent tooling#SDK