开发工具

研究介绍 Composer 2.5

产品认识全新的 Cursor

研究关于 Composer 2 的技术报告

研究推出 Composer 2

Blog

Blog

Blog

A practical guide to hill climbingAra Khan

One API key for Claude, Gemini, GPT, and everything elseTony Loehr

Prompts as playbooks; how infrastructure teams codify operational knowledgeAndrew Gardner

https://cline.bot/blog/the-invisible-trap-the-decisions-quietly-transferring-control-of-your-stack-to-model-providers

Announcing Cline Kanban: a CLI-agnostic app for multi-agent orchestration.Sidd Sant

20 one-shot prompts that turn Kanban into an autonomous coding machineTony Loehr

https://cline.bot/blog/archive

Architects or Tenants: Modern AI Stacks Are Being Built on Rented FoundationsSidd Sant • April 7, 2026You're b...

Cline mobile: how to vibe code from your phoneTony Loehr • April 15, 2026An engineer at Cline told me he was v...

Introducing Cline SDK: the upgraded agent runtime, and we rebuilt Cline upon itMay 13, 2026 • Renee Huang...

Blog

Blog

Aider blog

Staged publishing and new install-time controls for npm

Today we’re shipping two updates focused on supply-chain security for npm: Staged publishing is generally available. New --allow-* install source flags (--allow-file, --allow-remote, --allow-directory

Release v0.44.0-preview.0

What's Changed chore(release): bump version to 0.44.0-nightly.20260512.g022e8baef by @gemini-cli-robot in #26957 Changelog for v0.42.0 by @gemini-cli-robot in #26958 Refactor: Eliminate no-unsafe-retu

Release v0.43.0

What's Changed feat(core): steer model to use edit tool for surgical edits, fix a typo by @aishaneeshah in #26480 docs: clarify Auto Memory proposes memory updates and skills by @SandyTao520 in #26527

GitHub Copilot for Eclipse is open source

Following our previous updates, GitHub Copilot for Eclipse is open source, with the code available on GitHub under the MIT license. This marks an important milestone for GitHub Copilot in… The post Gi

v1.35.0

✨ Features Hooks system for extensible pre/post tool execution #9093 PreToolUse denial hook support #9304 /goal command for agent self-evaluation before finishing #9069 goose review local code review

Release v0.44.0-nightly.20260521.g57c42a5c4

What's Changed fix(core): enforce compile-time exhaustiveness in content-utils by @adamfweidman in #27207 feat(skills): add agent-tui and tui-tester skills by @adamfweidman in #27121 fix(context): Fix

Issue fields are now in public preview for all organizations

Issue fields are now available in public preview to all GitHub organizations on github.com and GitHub Enterprise Cloud with data residency. When you define typed metadata like Priority, Effort, or… Th

Copilot usage metrics reports now use GitHub-owned download URLs

As previously announced, the download URLs for Copilot usage metrics reports have migrated from Azure Front Door domains to a stable, GitHub-owned custom domain. This change improves URL stability and

Updates to available models in Copilot on web

We have updated our available model selection for Copilot Chat on the web to deliver more consistent, high-quality responses. What’s changed While model choice is valuable, we are limiting the… The po

Release v0.43.0-preview.1

What's Changed fix(patch): cherry-pick 85566a7 to release/v0.43.0-preview.0-pr-27073 [CONFLICTS] by @gemini-cli-robot in #27256 Full Changelog: v0.43.0-preview.0...v0.43.0-preview.1

Gemini 3.5 Flash is generally available for GitHub Copilot

Gemini 3.5 Flash, Google’s latest Flash-tier model, is now rolling out on GitHub Copilot. In our early testing, Gemini 3.5 Flash delivers near-Pro coding quality at Flash-tier speed and cost… The post

Semantic issue search in Copilot Chat

You can use natural language in GitHub Copilot Chat on web to quickly find, group, and analyze issues, with context-aware results powered by a new semantic issues index. What’s new… The post Semantic

Easily apply Copilot code review feedback with Copilot cloud agent

Copilot code review’s previous Implement suggestion button has now been renamed to Fix with Copilot and updated to support a UI dialog for more control over how suggestions are applied.… The post Easi

Upcoming deprecation of Python 3.9 for Dependabot

On June 23, 2026, Dependabot will no longer support Python version 3.9, which has reached its end-of-life. If you continue to use Python 3.9, there’s a risk that Dependabot will… The post Upcoming dep

Auto model selection now routes based on your task in VS Code

GitHub Copilot auto model selection now routes to the best model for your task, using utilization and model health metrics for a high quality, reliable, and token-efficient experience. How it… The pos

Release v0.44.0-nightly.20260518.g5611ff40e

What's Changed feat(core): add adk.agentSessionSubagentEnabled flag by @adamfweidman in #26947 Full Changelog: v0.44.0-nightly.20260517.g77e65c0db...v0.44.0-nightly.20260518.g5611ff40e

Composer 2.5

Release v0.44.0-nightly.20260517.g77e65c0db

What's Changed security: update dependencies to fix critical and high vulnerabilities by @scidomino in #27077 Fix/web fetch ctrl c abort by @ProthamD in #24320 fix(core): add aliases and thinking conf

Hermes Agent v0.14.0 (2026.5.16)

Hermes Agent v0.14.0 (v2026.5.16) Release Date: May 16, 2026 Since v0.13.0: 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community co

May 15, 2026Opus 4.7 for 33% less: How Auggie beats Claude Code on cost and qualityRobbert Kauffman, Mayur NagarshethRead

v1.34.1

🔧 Improvements Build non-vulkan linux variants using ubuntu 22.04 #9211

Release v0.44.0-nightly.20260514.g77078b3e8

What's Changed fix(ci): replace brittle --no-tag with explicit staging-tmp tag by @scidomino in #26940 Incremental refactor repo agent towards skills-based composition by @gundermanc in #26717 fix(ui)

Release v0.44.0-nightly.20260515.g928a311fb

What's Changed feat(core): expose RAG snippets to local log file for debugging by @spencer426 in #27016 fix(acp/auth): prevent conflicting credentials on enterprise gateways and support optional API k

v0.14.22

Release Notes [2026-05-14] llama-index-agent-agentmesh [0.2.0] mass uv lock --upgrade (#21638) llama-index-callbacks-agentops [0.5.0] chore(deps): bump the pip group across 55 directories with 3 updat

v1.34.0

✨ Features Hooks support for customizable agent behavior #9093 Agents CRUD operations #9084 Projects as backend sources with system prompt injection #8739 Auto-updating for plugins #9061 Linux Vulkan

1.44.0

What's Changed refactor(telemetry): track btw side question as tool_call event by @jackfish212 in #2257 chore(release): bump kimi-cli and kimi-code to 1.44.0 by @jackfish212 in #2262 Full Changelog: 1

May 12, 2026Excited, anxious, invigorated: what 219 engineering leaders told us about going AI-nativeVinay Perneti, Emma WebbRead

announcement

Release v0.43.0-preview.0

What's Changed feat(core): steer model to use edit tool for surgical edits, fix a typo by @aishaneeshah in #26480 docs: clarify Auto Memory proposes memory updates and skills by @SandyTao520 in #26527

Release v0.42.0

What's Changed fix(cli): prevent automatic updates from switching to less stable channels by @Adib234 in #26132 chore(release): bump version to 0.42.0-nightly.20260428.g59b2dea0e by @gemini-cli-robot

1.43.0

What's Changed feat(ui): improve shell spacing, link highlighting and notification duration by @jackfish212 in #2230 feat(telemetry): polish event schema with outcome enum, lifecycle tracking and erro

1.42.0

What's Changed fix(soul): clear partial UI output when LLM step is retried by @7Sageer in #2177 fix(tests): unbreak main CI after #2177 by @7Sageer in #2213 fix(shell): register /btw slash command by

LatestBlackbox Encrypted AI: Confidential LLMs at 22× Lower CostEnd-to-end encrypted LLM inference with hardwa...

Hermes Agent v0.13.0 (2026.5.7) — The Tenacity Release

Hermes Agent v0.13.0 (v2026.5.7) Release Date: May 7, 2026 Since v0.12.0: 864 commits · 588 merged PRs · 829 files changed · 128,366 insertions · 282 issues closed (13 P0, 36 P1) · 295 community contr

How Cosmos Accelerated our AI-Native Transformation by Removing the Code Review BottleneckMay 6, 2026How Cosmo...

We don't need more agents.

Introducing Augment Prism: model routing to reduce cost and maintain qualityMay 2, 2026Introducing Augment Pri...

Hermes Agent v0.12.0 (2026.4.30)

Hermes Agent v0.12.0 (v2026.4.30) Release Date: April 30, 2026 Since v0.11.0: 1,096 commits · 550 merged PRs · 1,270 files changed · 217,776 insertions · 213 community contributors (including co-autho

Karpathy skills on OpenClaw: agents don't write better code.

1.41.0

What's Changed fix(clipboard): enable clipboard paste on headless Linux over SSH by @ZichenWen1 in #2115 fix(plugin): support installing from .zip URL by @tempurai in #2126 chore(release): bump kimi-c

AI transformation is a systems problem: a conversation with Justin Reock, DXApr 28, 2026AI transformation is a...

v1.33.1

🐛 Bug Fixes Remove Windows CUDA build variant from release pipeline #8895 Windows CLI updates now use standard asset instead of CUDA variant #8895

v1.33.0

chore(release): open release branch for 1.33.0

kosong-0.53.0

chore(release): bump kimi-cli to 1.40.0 and kosong to 0.53.0 (#2108)

1.40.0

What's Changed fix(shell): show active agent task count in prompt status bar by @wbxl2000 in #2041 fix(auth): recover OAuth flows after transient failures by @wbxl2000 in #2060 fix(shell): correct /us

v2.0-rc-04-27-0

chore: enabled auto merge for dependabot prs if they passes the ci ch…

v2.0.0-rc-04-27-0

chore: enabled auto merge for dependabot prs if they passes the ci ch… …ecks (#8856)

Hermes Agent v0.11.0 (2026.4.23)

Hermes Agent v0.11.0 (v2026.4.23) Release Date: April 23, 2026 Since v0.9.0: 1,556 commits · 761 merged PRs · 1,314 files changed · 224,174 insertions · 29 community contributors (290 including co-aut

1.39.0

What's Changed fix(shell): approval request text input should render caret correctly by @kermanx in #2005 feat(kimi): add KIMI_MODEL_THINKING_KEEP env for preserved thinking by @RealKai42 in #2029 fea

kosong-0.52.0

chore(release): bump kimi-cli 1.39.0 and kosong 0.52.0 (#2054)

A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all.Apr 22, 2026A good AGENTS.md is a...

v1.32.0

✨ Features Exa AI-powered search tool #8487 Desktop notification when goose finishes a task #8647 @agent mention support in chat #8571 /skills command #8600 Associate threads with projects #8745 Auto-

1.38.0

What's Changed feat(telemetry): integrate telemetry tracking across interactive and … by @RealKai42 in #1798 fix(kosong/anthropic): merge parallel tool_results into one user msg by @wbxl2000 in #1978

kosong-0.51.0

chore(release): bump kimi-cli to 1.38.0 and kosong to 0.51.0 (#2009)

v2-rc.1

clean up

v0.14.21

Release Notes [2026-04-21] llama-index-callbacks-honeyhive [0.5.0] chore(deps): bump the pip group across 87 directories with 2 updates (#21382) chore(deps): bump the pip group across 68 directories w

v1.31.1

No content.

Hermes Agent v0.10.0 (2026.4.16)

Hermes Agent v0.10.0 (v2026.4.16) Release Date: April 16, 2026 The Tool Gateway release — paid Nous Portal subscribers can now use web search, image generation, text-to-speech, and browser automation

Hermes Agent v0.9.0 (v2026.4.13)

Hermes Agent v0.9.0 (v2026.4.13) Release Date: April 13, 2026 Since v0.8.0: 487 commits · 269 merged PRs · 167 resolved issues · 493 files changed · 63,281 insertions · 24 contributors The everywhere

The era of single-model engineering is overApr 7, 2026The era of single-model engineering is overApr 7, 2026

Hermes Agent v0.8.0 (v2026.4.8)

Hermes Agent v0.8.0 (v2026.4.8) Release Date: April 8, 2026 The intelligence release — background task auto-notifications, free MiMo v2 Pro on Nous Portal, live model switching across all platforms, s

The AI-native transformation path, end to endApr 7, 2026The AI-native transformation path, end to endApr 7, 2026

Hermes Agent v0.7.0 (v2026.4.3)

Hermes Agent v0.7.0 (v2026.4.3) Release Date: April 3, 2026 The resilience release — pluggable memory providers, credential pool rotation, Camofox anti-detection browser, inline diff previews, gateway

v0.14.20

Release Notes [2026-04-03] llama-index-agent-agentmesh [0.2.0] fix vulnerability with nltk (#21275) llama-index-callbacks-agentops [0.5.0] chore(deps): bump the uv group across 50 directories with 2 u

Designing with code, without writing codeApr 2, 2026Designing with code, without writing codeApr 2, 2026

Frontier AI at half the cost: Gemini 3.

Agents Window

Hermes Agent v0.6.0 (v2026.3.30)

Hermes Agent v0.6.0 (v2026.3.30) Release Date: March 30, 2026 The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, t

Hermes Agent v0.5.0 (v2026.3.28)

Hermes Agent v0.5.0 (v2026.3.28) Release Date: March 28, 2026 The hardening release — Hugging Face provider, /model command overhaul, Telegram Private Chat Topics, native Modal SDK, plugin lifecycle h

v0.14.19

Release Notes [2026-03-25] llama-index-agent-agentmesh [0.2.0] chore(deps): bump the uv group across 49 directories with 1 update (#21083) llama-index-callbacks-argilla [0.5.0] chore(deps): bump the u

Composer 2

v0.14.18

Release Notes [2026-03-16] llama-index-agent-agentmesh [0.2.0] chore: deprecate python 3.9 once and for all (#20956) llama-index-agent-azure [0.3.0] chore: deprecate python 3.9 once and for all (#2095

v0.14.16

Release Notes [2026-03-10] llama-index-core [0.14.16] Add token-bucket rate limiter for LLM and embedding API calls (#20712) Fix/20706 chonkie init doc (#20713) fix: pass tool_choice through FunctionC

v0.14.15

Release Notes [2026-02-18] llama-index-agent-agentmesh [0.1.0] [Integration] AgentMesh: Trust Layer for LlamaIndex Agents (#20644) llama-index-core [0.14.15] Support basic operations for multimodal ty

02Claude Opus 4.6 Is Now Live on BLACKBOX AIAnthropic just shipped their latest flagship model — and it's alre...

v0.14.14

Release Notes [2026-02-10] llama-index-callbacks-wandb [0.4.2] Fix potential crashes and improve security defaults in core components (#20610) llama-index-core [0.14.14] fix: catch pydantic Validation

03What is Agentic Development?

04AI Agents vs AI Assistants: Why Copilots Are Already OutdatedYour AI assistant is holding you back.

05Blackbox AI Agents API: The Complete Developer GuideHarness multiple AI coding agents programmatically, orch...

v0.14.13

Release Notes [2026-01-21] llama-index-core [0.14.13] feat: add early_stopping_method parameter to agent workflows (#20389) feat: Add token-based code splitting support to CodeSplitter (#20438) Add Ra

06Multi-Agent Execution: Why Running Multiple AI Agents Beats Single-Agent AIWhat if you could run 5 AI develo...

07From Prompt to Production: How AI Agents Ship Code Without Human InterventionI typed one sentence.

08Blackbox AI vs Devin: Accessible AI Agents vs $500/Month PremiumDevin costs $500/month.

09How to Assign Tasks to AI Coding Agents: A Practical GuideStop writing code.

10AI Agents for Engineering Teams: How to 10x Your Team's OutputWhat if every developer on your team had 5 AI...

v0.14.12

Release Notes [2025-12-30] llama-index-callbacks-agentops [0.4.1] Feat/async tool spec support (#20338) llama-index-core [0.14.12] Feat/async tool spec support (#20338) Improve MockFunctionCallingLLM