Harness Hub

What's new

New in the directory

What joined Harness Hub lately, which projects shipped a major version, what they have released, and what our discovery bot has spotted but nobody has reviewed yet.

Added this week

12 companies · 127 open source · 156 skills, plugins & mods · 124 events

Companies · 12

AI coding agents that let non-engineering teams ship work, and an orchestration platform for them.

A code change verification agent: risk-rated PR reviews and CI fixes that iterate until the build is green.

Hosted OpenClaw: a personal OpenClaw agent running on its own cloud VM.

An AI DevOps engineer that fixed CI failures, triaged incidents and reviewed code ("Platform engineering on autopilot").

A control plane for an AI software factory: governed, stateful agent workflows across the software lifecycle.

An agent environment from the lakeFS team: a versioned filesystem, credentials and tools for AI agents.

and 6 more entries in Companies

Open source · 127

Self-hosted workflows for orchestrating coding agents with scripts and approval gates.

An open-source terminal coding agent for large projects and real-world tasks (cloud wound down in October 2025).

Self-hosted multi-harness, multi-agent engine for teams

git worktrees + tmux windows for zero-friction parallel dev: one command per isolated agent task.

Open-source IDE platform with Theia AI, a vendor-neutral AI harness.

Open-source workflow automation with AI agents and MCP servers

and 121 more entries in Open source

Skills, plugins & mods · 156

MCP server and CLI for agents to see and control Android phones and iPhones.

Enterprise architecture governance commands for AI coding assistants

Skills for coding agents to build games and engine-rendered projects

MCP server that lets agents browse and debug web pages with Firefox

Claude Code plugin for game sprites matched to camera angle and art style

Plugin that makes coding agents follow project rules

and 150 more entries in Skills, plugins & mods

Events · 124

and 118 more entries in Events

Added in the last 30 days

217 companies · 372 open source · 360 skills, plugins & mods · 344 events

Companies · 217

AI coding agents that let non-engineering teams ship work, and an orchestration platform for them.

A code change verification agent: risk-rated PR reviews and CI fixes that iterate until the build is green.

Hosted OpenClaw: a personal OpenClaw agent running on its own cloud VM.

An AI DevOps engineer that fixed CI failures, triaged incidents and reviewed code ("Platform engineering on autopilot").

A control plane for an AI software factory: governed, stateful agent workflows across the software lifecycle.

An agent environment from the lakeFS team: a versioned filesystem, credentials and tools for AI agents.

and 211 more entries in Companies

Open source · 372

Self-hosted workflows for orchestrating coding agents with scripts and approval gates.

An open-source terminal coding agent for large projects and real-world tasks (cloud wound down in October 2025).

Self-hosted multi-harness, multi-agent engine for teams

git worktrees + tmux windows for zero-friction parallel dev: one command per isolated agent task.

Open-source IDE platform with Theia AI, a vendor-neutral AI harness.

Open-source workflow automation with AI agents and MCP servers

and 366 more entries in Open source

Skills, plugins & mods · 360

MCP server and CLI for agents to see and control Android phones and iPhones.

Enterprise architecture governance commands for AI coding assistants

Skills for coding agents to build games and engine-rendered projects

MCP server that lets agents browse and debug web pages with Firefox

Claude Code plugin for game sprites matched to camera angle and art style

Plugin that makes coding agents follow project rules

and 354 more entries in Skills, plugins & mods

Events · 344

and 338 more entries in Events

Major updates

Projects that moved to a new major version in the last 30 days, then the most-starred 0.x projects that started a new minor series (which semver allows to break things).

  1. claude-memv15.21.0 →v16.0.0Major versionPlugin

    · 3d ago

    My Work puts what needs you first My Work, the page that shows what your agents are doing, was rebuilt from a full UI review (#6210, #6304). What needs you sits at the top, long lists fold, and every page works on a phone, by keyboard and with a screen reader. What needs you…

  2. ragflowv0.27.3 →v1.0.0-rc3Major version

    · 3w ago

    1.0.0-rc3 is the third and final release candidate before the official v1.0.0 release. It fixes several issues found in rc2 and introduces new features and enhancements. Key updates: Introduced the decision model for evidence sufficiency judgment within the agentic tool loop,…

  3. OpenSpecv1.17.0 →v2.0.0Major versionMod

    · 10d ago

    OpenSpec 2.0 OpenSpec now installs skills in .agents/skills/ instead of keeping a separate copy for each coding agent. Tools that don't read this folder, like Claude Code and Kiro, get links to the same skills. We're also removing the /opsx: slash commands. Each command already…

  4. Humanizerv3.1.0 →v4.0.0Major versionSkill

    · 11d ago

    Humanizer 4.0.0 lets the skill add a specific detail where the text is generic, and it rewrites the skill's own instructions and examples to be clearer. A rewrite may now contain a detail that was not in your text. If you rely on the old rule, stay on v3.1.0. What changed The…

  5. Agentic Awesome Skills (AAS)v20.11.0 →v21.0.0Major versionSkill

    · 3d ago

    npm unavailable: This version is not published to npm; package distribution and full release alignment remain incomplete. [21.0.0] - 2026-11-18 - "50K on GitHub and 3,000+ Skills" GitHub's public counter now shows 50k stars, and Agentic Awesome Skills includes 3,022 catalog…

  6. oh-my-piv18.22.2 →v19.0.0Major version

    · 2d ago

    @oh-my-pi/pi-agent-core Added Added support for excluding custom messages from model context and compaction or branch summaries, while allowing queued steering and follow-up messages to continue correctly after excluded messages. @oh-my-pi/pi-ai Added Added a prewarm stream…

  7. Nuwa Skillv1.1.0 →v2.0.0Major versionSkill

    · 11d ago

    这一版改了什么 女娲的目标从「造出来像不像」改成「比不装 Skill 的模型多出什么」。 先写先验快照:调研之前,先把模型不查资料就知道的内容写下来。调研只找三种东西:推翻它的、比它深的、它没有的。 产物分三层:350 行以内的 SKILL.md、案例库 references/casebook.md、原话库 references/voice.md。新增招式(遇到某类问题他具体怎么做)、常见误读、边界三格,每个 Skill 自带七条运行纪律,比如「材料里没有,不等于他没说过」「原话和推演分开说」。 验证改成盲测:独立 agent 用同一组任务题,带…

  8. Parlantv3.3.2 →v4.0.2Major version

    · 2w ago

    [4.0.2] - 2026-11-05 Added The chat widget lets the AI agent in a visitor's browser talk to your agent over WebMCP (document.modelContext; in Chrome behind a flag today). On every page it's on, the widget registers an ask_agent tool described with the agent's name. A call…

  9. Phoenixarize-phoenix-v21.3.0 →arize-phoenix-v22.0.0Major version

    · yesterday

    22.0.0 (2026-11-20) MIGRATION Features add type column to generative_models (3047aab) cost-tracking: calculate costs for DECISION spans (#17764) (0f83453) cost-tracking: calculate costs for EMBEDDING spans (#17788) (0f39d64) cost-tracking: expose generative model type in…

  10. oh-my-hermesomher-v0.2.14 →omher-v1.0.0Major versionMod

    · 3d ago

    omher 1.0.0, the desktop app for your Hermes bots. If Hermes Agent is not installed yet, omher offers to install it (with oh-my-hermes) on first launch. macOS: run curl -fsSL https://omher.app/omher sh in Terminal. It installs this build with no security prompt. macOS dmg…

  11. SkillEvaluatorv0.9.0 →v1.0.0Major versionSkill

    · 4d ago

    Superseded by SkillEvaluator v1.0.1. Use v1.0.1 for the published Python package, CI bundle, and complete release assets. Original v1.0.0 release notes SkillEvaluator v1.0.0 🎉 SkillEvaluator v1.0.0 marks our first major release. Understand how your skills load, measure how…

  12. CCometixLinev1.1.2 →v2.0.0Major versionPlugin

    · 4w ago

    [2.0.0] - 2026-10-24 Added layout: Report the steps taken to fit a line layout: Wrap lines too wide for the terminal metrics: Add trend, auto-compact, run-out, spend rate and rewarm metrics metrics: Add cmd items for user commands metrics: Declare each metric's options metrics:…

  13. brooks-lintv1.9.1 →v2.0.0Major versionPlugin

    · 4d ago

    This version updates the Health, Sweep, and CI review contracts. See the migration guide below before upgrading. Breaking changes Action consumers must handle skipped=true and an empty score for an empty diff instead of treating the result as numeric zero. CI accepts review…

  14. Bernsteinv3.24.1 →v4.0.0Major version

    · yesterday

    Bernstein 4.0.0 At a glance If a workflow node fails, Bernstein skips later layers, including independent branches, as in bernstein workflow resume. A detached SSH task with a nonzero remote exit fails the run and leaves later tasks pending. bernstein govern audit --strict…

  15. unbrowsev12.5.0 →v13.0.0Major versionPlugin

    · 3d ago

    On a Mac, download the disk image: Unbrowse-macos-arm64.dmg for Apple silicon, Unbrowse-macos-x64.dmg for Intel. Open it and drag Unbrowse onto Applications: the app holds the window, the node, unb and the browser program the node fetches when a goal first needs it. It is…

Latest releases

  1. open-knowledgev0.89.14Skill

    · yesterday

    Patch Changes Moving or renaming a page to a name already open in an editor now shows the moved page there instead of an empty one, and a later edit to it keeps the page's body and other properties. The bundled third-party notices now credit the KaTeX and Excalidraw fonts,…

  2. Claude Skills (Jeffallan)v0.4.21Skill

    · yesterday

    Added nuxt-expert: Nuxt 4.6 skill for full-stack Nuxt apps, with references on project structure and upgrades (Nuxt 3 to 4, the Nuxt 5 compatibility flag), data fetching, server routes with nuxt/server, rendering (route rules, islands, lazy hydration), security (runtime config…

  3. ai-maestrov0.106.253Skill

    · yesterday

    Two fixes to the "startup blocked" check (0.106.249). Details are in CHANGELOG.md. It now fires (0.106.252). The check took Claude Code's ⏵⏵ mode footer for the input box, so every screen read as Ready. An unnumbered menu, such as the first-run theme picker, did too. Now a…

  4. Graphifyv0.9.114Skill

    · yesterday

    Performance work on the extract/build/update pipeline, plus a batch of extractor and build fixes. Every entry marked Perf preserves graph output exactly (byte-identical); the extractor fixes change output and share one AST cache schema bump (see the note at the end). Perf: ids…

  5. reticlev3.10.9Skill

    · yesterday

    Fixed @reticlehq/browser — the HUD settings switches had no accessible name. Each switch and checkbox in the settings panel had no text and no aria-label. A screen reader said only "switch", and an accessibility audit of the app counted the HUD controls as unnamed. Each control…

  6. GStackv1.102.1.0Skill

    · yesterday

    gstack 1.102.1.0 closes a gap where a secret written after a slash could be printed unhidden, locks down gstack's usage reporting and makes it more useful for people who opt in, fixes a set of bugs in how gstack picks the right skill for a prompt, and makes a gstack skill's…

  7. planning-with-filesv3.29.0Skill

    · yesterday

    Added Choose whether to enroll a plan for checkbox-only re-attestation. The shell helper accepts eligible checkbox changes after enrollment and checks them against the same snapshot it hashes. Fixed Completion reports count statuses inside each phase. Fenced examples and quoted…

  8. sno-station-skillsv1.0.42Skill

    · yesterday

    Sno Station skills 1.0.42 The team skills your agents share: peer review, handoff, delegation, reporting and learning from mistakes. Install them with sno setup. Already installed? Run sno update.

  9. Obsidian Skills1.2.1Skill

    · yesterday

    The Obsidian skills now load in Grok Bot. Plugin Cursor manifest: declared the skills/ folder, which Grok Bot needs to find the skills (#163). Thanks @davidabrooks!

  10. obsidian-skills1.2.1Skill

    · yesterday

    The Obsidian skills now load in Grok Bot. Plugin Cursor manifest: declared the skills/ folder, which Grok Bot needs to find the skills (#163). Thanks @davidabrooks!

  11. Vercel Agent Skillsagent-skills-5a37a6329fbad3666c3207392a6a7c0110e92efbSkill

    · yesterday

    Automated Agent Skills discovery release for 5a37a6329fbad3666c3207392a6a7c0110e92efb.

  12. Agentic Awesome Skills (AAS)v21.1.0Skill

    · yesterday

    npm unavailable: This version is not published to npm; package distribution and full release alignment remain incomplete. [21.1.0] - 2026-11-20 - "Design Systems, Motion, and Agent Workflows" Add 33 skills for design systems, creative production, local inference, engineering…

  13. oil-uiv0.34.3Skill

    · yesterday

    更新检查支持付费版附赠的配套 Skill,并调整生图积分门槛。 scripts/check_update.py:付费版有已发布的附赠 Skill、同目录却没有安装时会提示,你同意后用固定的 oil-cli 补装;开源版本身不受影响。 升级固定的 oil-cli 提交至 0.4.0。 生图:Oil 生图余额不少于 3 积分时才视为可用(文生图 1K/2K/4K 为 3/6/9 积分)。 oiloil-image.mjs:被限流(HTTP 429)时给出明确提示和建议的重试时间,不扣费。

  14. one-skill-to-rule-them-allv3.12.0Skill

    · yesterday

    This release merges the release/v3.12.0 test line after one test week. Most of its changes were exercised during that week or checked with a fixture. Seven were not exercised and ship untested, and two were exercised and do not hold yet; both groups are named below. What…

  15. comet0.5.6Skill

    · yesterday

    What's Changed feat: improve workflow handoffs and Dashboard workspaces by @benym in https://github.com/rpamis/comet/pull/583 Added Scoped workflow context: Deliver applicable project policies and personal memory to Native and Classic implementers and verifiers using the…

  16. SkillHubv0.2.28Skill

    · yesterday

    SkillHub v0.2.28 This release improves skill discovery across platform and GitHub sources, introduces repository snapshots and batch moderation, and adds more explicit token permissions and opt-in team-only automatic publication. 🌟 Highlights Explore platform skills and…

  17. open-sciencev1.3.2Skill

    · yesterday

    AIPOCH Open-Science v1.3.2 Lighter long conversations, Kilo Gateway as an official provider, image model catalogs you can check, reliable first messages in agent sessions, and PDF translation that keeps the native layout. AIPOCH Open-Science is an open-source, local-first,…

  18. last30daysv4.4.0Skill

    · yesterday

    What's Changed fix(watchlist): pass scheduled topics as literal research text by @iliaal in https://github.com/mvanhorn/last30days-skill/pull/1514 fix(mcp): honor save=false for local research artifacts by @iliaal in https://github.com/mvanhorn/last30days-skill/pull/1515…

  19. Marketing Skillsv2.14.25Skill

    · yesterday

    Community batch: fourteen new tool guides, three guide updates, and three skill contributions. New integration guides, each reviewed against the usefulness and neutrality rules in tools/PARTNERS.md: Hermoso (#1014), Calven (#980), PostOnce (#979), GetYouTubeTranscript (#975),…

  20. LangChain Skillsv0.3.0Skill

    · 2d ago

    What's Changed fix(langchain-eval-engineering): allow agent fixes for product failures in run phase by @robin-agent[bot] in https://github.com/langchain-ai/langchain-skills/pull/103 fix(langchain-agent-monitoring): document create-decision-model --group-by support by…

  21. skill-recorderv0.9.3Skill

    · 2d ago

    Commit-pinned installation Copy the complete command for your operating system into PowerShell (Windows) or Terminal (macOS/Ubuntu). Use the same command to install or update. Windows 11 x64 or ARM64 Windows finishes installation without automatically opening the app. Finish…

  22. Impeccableengine-v0.1.28Skill

    · 2d ago

    Prebuilt impeccable engine binaries (engine-v0.1.28). The launcher, the npm shim and impeccable install download these on first run. Docs: https://impeccable.style

  23. stop-that-shit0.2.6Skill

    · 2d ago

    Stop That Shit 0.2.6 — 任务边界与 DeepSeek Harness 新增与修复 DeepSeek Harness Guard 预览。 适配 DSH 0.2.2-rc.3 的 Web Standard 预设。Guard 使用宿主提供的根会话和执行目录检查任务范围,覆盖只读模式、文件范围和可选的 apply_patch。修正了插件市场查询与定时任务的分类。安装包为 stop-that-shit-dsh-0.2.6.tgz,通过 DSH 的 web profile 安装。 Codex 子代理继承父任务边界。…

  24. terraform-skillv1.18.2Skill

    · 2d ago

    1.18.2 (2026-11-19) Bug Fixes install the nested skill dir for Cursor, Copilot, Kiro and Antigravity (#68) (c666a43)

  25. obsidian-wikiv2026.11.7Skill

    · 2d ago

    What's Changed feat(server): self-host in one command — serve, pulled image, TLS profile, read-only key, two-way git sync by @Ar9av in https://github.com/Ar9av/obsidian-wiki/pull/341 fix(batch): plan a named source folder even when .okignore lists it (#344) by @Ar9av in…

  26. Agent Skills (Osmani)0.6.17Skill

    · 3d ago

    Agent Skills 0.6.17 adds an accessibility-engineering skill for auditing and fixing WCAG 2.2 AA issues, fixes a rollback workflow that could never log in, and lets you regrade eval runs without paying for them again. New skill accessibility-engineering (#261, @Chukwuebuka-2003,…

  27. Tech Leads Club Agent Skillsskills-catalog-v0.17.21Skill

    · 3d ago

    0.17.21 (2026-11-18) 🚀 Features skills-catalog: record the request and the fix pass in tlc-spec-lean (586a794ef) skills-catalog: bump tlc-spec-lean to 3.1.0, leave implementation to the model (dd6878eb6) 🩹 Fixes skills-catalog: keep tlc-spec-lean scripts from crashing on…

  28. stack-diagramv0.7.0Skill

    · 3d ago

    What's Changed feat(stack-diagram): add Databricks product icons by @anibaljasin in https://github.com/caru-ini/stack-diagram/pull/6 feat: allowlist kubernetes community and cncf artwork icons in gallery by @muadzhdz in https://github.com/caru-ini/stack-diagram/pull/10 New…

  29. darwin-skillv3.0.2Skill

    · 3d ago

    针对 #31 反馈的长耗时,修了计票工具的几个问题,并补上流程说明。棘轮的裁决规则没有变。 修复 darwin.py tally 的重跑提醒只列重跑后可能改变裁决的条目。之前一条输了的测试即使翻盘也不影响 keep,也会要求重跑。 留出集和增益评审不再提示重跑。留出集按流程只跑一次。 评委没交票或票文件没写完整时,一次列出所有要补的评委。之前只报第一位,票文件损坏时直接报错退出。 流程 同一步的执行者和评委互不依赖,runtime 支持并发就一次派出。 每轮最多重跑一次。 新增评委卡死的处理:只重派没交票的那几位,已交的票不动。 成本说明订正:2 条…

  30. SkillEvaluatorv1.0.1Skill

    · 3d ago

    🎉 Introducing SkillEvaluator v1.0.1, our first complete release in the 1.0 series. Understand how your skills load, measure how they perform, and bring automated evaluation into your workflow with HarnessCheck, NeMo Gym integration, and improved agent-assisted evaluation and…

From GitHub releases (or tags) of every project in the directory, checked nightly. Follow along with the Atom feed.

On our radar

UnreviewedSpotted by our discovery bot — not yet reviewed. Stars come from GitHub and are not checked; we have not tried any of these, so look before you install.

Nothing on the radar right now.

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.