paperclipai
Paperclip CLI â orchestrate AI agent teams to run a business
Why this rank:Strong adoptionRecent releaseHealthy release cadence
Description
Paperclip CLI â orchestrate AI agent teams to run a business
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| v2026.1023.0 | # Paperclip v2026.1023.0 > Released: 2026-10-23 Paperclip v2026.1023.0 carries 200 commits, promoted from `2026.1012.1-beta.0`. The headline is private work: a task or project can now be marked private and shared with named people and agents; everyone else cannot open it, find it in task lists or search, read its run transcripts, or reach it through a plugin. Around that: agents can run through your own model gateway (OpenRouter, Amazon Bedrock, Google Gemini, or any OpenAI Responses, Anthropi | High | 10/24/2026 |
| v2026.1012.0 | # Paperclip v2026.1012.0 > Released: 2026-10-12 Paperclip v2026.1012.0 carries 130 commits, promoted from `2026.1006.0-beta.0`. The headline is that outside assistants can now join your team: Claude Code, Codex, OpenCode, and any MCP client can connect to Paperclip as a signed-in person, review work, and delegate tasks, all behind an experimental setting. Around that: Chat leads the navigation with each agent's tasks and artifacts beside the conversation, the Connections catalog pulls in accou | High | 10/12/2026 |
| v2026.1005.0 | # Paperclip v2026.1005.0 > Released: 2026-10-05 Paperclip v2026.1005.0 carries 179 commits, promoted from `2026.1002.0-beta.0`. The headline is agents that carry more with them: Grok Build runs on the native runner, agents keep their own files across tasks, company skills sync from GitHub repositories, and Browser Use Cloud gives agents a live browser that people can watch and take over from the task. Around those: most connectors now set up in one click with MCP aggregators on by default, Sla | High | 10/6/2026 |
| v2026.1001.0 | # Paperclip v2026.1001.0 > Released: 2026-10-01 Paperclip v2026.1001.0 carries 77 commits, promoted from `2026.921.0-beta.1`. The headline is reliability: a deep hardening pass over the native runner and chat recovery â approval and Stop races, session continuity, sandbox reconnection and cleanup â alongside a friendlier face: agent personas throughout the app, an animated onboarding character, and a rebuilt Slack setup. Around those: agents can review GitHub pull requests as scheduled review | High | 10/2/2026 |
| v2026.916.1 | # Paperclip v2026.916.1 > Released: 2026-09-21 A patch on top of [2026.916.0](https://github.com/paperclipai/paperclip/releases/tag/v2026.916.0) that fixes sending messages in the task conversation view. It carries one targeted fix (plus its regression tests and a small server error-classification repair that rode along in the same commit); everything else in 2026.916.0 is unchanged. ## Fixes - **The chat composer's send button no longer starts out disabled on desktop.** The task page disabl | High | 9/21/2026 |
| v2026.916.0 | # Paperclip v2026.916.0 > Released: 2026-09-16 Paperclip v2026.916.0 carries 503 commits, promoted from `2026.916.0-beta.0` published the same day. The headline is the Connections train: AI runtime credentials â Claude and Codex subscriptions, API keys, shared accounts â now live in Connections under the same grants and permission boundaries as every other account, follow the responsible person through hiring and task execution, and can be connected or repaired inline from the task that needs | High | 9/16/2026 |
| v2026.831.1 | # Paperclip v2026.831.1 > Released: 2026-09-02 A patch on top of [2026.831.0](https://github.com/paperclipai/paperclip/releases/tag/v2026.831.0) that fixes first-run onboarding. It carries a single targeted change; everything else in 2026.831.0 is unchanged. ## Fixes - **Onboarding no longer gets stuck on the organization step.** On the first onboarding screen ("What is the name of your organization?"), clicking **Continue** created the organization on the server but could leave the wizard s | Medium | 9/2/2026 |
| v2026.824.1 | # Paperclip v2026.824.1 > Released: 2026-08-25 Paperclip v2026.824.1 is a patch release on v2026.824.0 that repairs the background-service leg of onboarding end to end: the service now actually starts from an `npx` onboard, onboarding no longer steers you into a safety-check error afterward, and it finishes by handing you the dashboard in your browser. ## Fixes - **Accepting the background-service prompt during an `npx` onboard no longer installs a broken service.** The service definition ta | High | 8/25/2026 |
| v2026.817.0 | # Paperclip v2026.817.0 > Released: 2026-08-17 Paperclip v2026.817.0 is the first stable release since 2026.722.0 â and the first stable ever published through the new canary â nightly â beta â stable release channels. This exact build shipped as a canary, was smoke-tested and promoted to nightly, soaked as `2026.811.0-beta.0`, and only then was promoted to stable. It carries 311 commits spanning a first-class Decisions workflow, full-fidelity company Import/Export, a managed CLI install lifec | High | 8/18/2026 |
| v2026.722.0 | # Paperclip v2026.722.0 > Released: 2026-07-22 ## Highlights - **Run-bound agent secret access** â Agents can now fetch the secrets they've been granted on demand through a run-bound API, instead of relying only on ambient environment injection. A new `access.*` delivery mode exposes API-only secrets, `GET /api/agents/me/secrets` lists just the aliases an agent is granted, and `POST /api/agents/me/secrets/:key/value` returns a value with `Cache-Control: no-store`. Every value read is written | Medium | 7/22/2026 |
| v2026.720.0 | # Paperclip v2026.720.0 > Released: 2026-07-20 ## Highlights - **Skill Studio & skill organization** â A three-pane skill IDE with sandboxed test runs, so you can author, edit, and try out skills without leaving Paperclip. Skills now organize into nested folders with a dedicated "My Skills" view, you can import skills straight from a project, and company skill policy is open-by-default with core UX for tightening it. Company skill forks run prechecks before they land, and markdown edits get p | High | 7/20/2026 |
| v2026.707.0 | # Paperclip v2026.707.0 > Released: 2026-07-07 This release lands **89 commits from 8 contributors**. ## Highlights - **User-specific runtime secrets** - Secrets can now be scoped to the individual human operator, not just the company. Define user-specific secret definitions, store per-user values, bind them to environments, and â thanks to new responsible-user run attribution â have Paperclip deterministically check that the human behind a run has actually supplied the value a run needs bef | High | 7/7/2026 |
| v2026.626.0 | # Paperclip v2026.626.0 > Released: 2026-06-26 This release lands **122 commits from 17 contributors**. ## Highlights - **Hermes, now built in (local & remote gateway)** - Hermes is a first-class adapter in this release. Hire `hermes_local` agents that run on your own machine, or `hermes_gateway` agents that run Hermes **remotely** through a gateway â no manual plugin install required, with secure onboarding defaults for the gateway URL and API key. External Hermes packages can still overrid | High | 6/27/2026 |
| v2026.618.0 | # Paperclip v2026.618.0 > Released: 2026-06-18 ## Highlights - **Skills Store** - Browse, install, and manage agent skills from a dedicated in-app store, so you can give your agents new capabilities without hand-wiring files. Skills are now a first-class, installable unit with install counts and a company-scoped catalog. ([#7990](https://github.com/paperclipai/paperclip/pull/7990), @cryppadotta) - **Self-hostable sandbox execution** - Cloud/sandboxed agent execution matures: a self-hostable K | High | 6/18/2026 |
| v2026.609.0 | # v2026.609.0 > Released: 2026-06-09 ## Highlights - **Company Artifacts** - Files, media, and documents your agents produce are now first-class. A new company-scoped Artifacts page indexes every work product across issues and runs, groups them by task stack by default, and supports upload and rich playback â including video artifact thumbnails â so you can inspect what your agents made without opening each issue one by one. ([#7621](https://github.com/paperclipai/paperclip/pull/7621), [#7654 | High | 6/9/2026 |
| v2026.529.0 | # v2026.529.0 > Released: 2026-05-29 ## Highlights - **Inline document annotations and comments** - Issue documents now support inline, revision-aware annotation threads with comments and stable anchor snapshots, so agents and operators can discuss a specific passage instead of leaving detached issue comments or editing the whole document. ([#6733](https://github.com/paperclipai/paperclip/pull/6733), @cryppadotta) - **Company skills CLI and catalog management** - Skills are now first-class: i | High | 5/30/2026 |
| v2026.525.0 | # v2026.525.0 > Released: 2026-05-25 ## Highlights - **Modal sandbox provider is now a first-party plugin** - Paperclip ships a Modal sandbox-provider plugin so companies can run agents on Modal's managed sandboxes alongside E2B, Cloudflare, and Daytona, with CI publishing and cold-start-friendly probe timeouts wired in. ([#6245](https://github.com/paperclipai/paperclip/pull/6245), [#6289](https://github.com/paperclipai/paperclip/pull/6289), [#6290](https://github.com/paperclipai/paperclip/pu | High | 5/25/2026 |
| v2026.517.0 | # v2026.517.0 > Released: 2026-05-17 ## Highlights - **Grok Build is now a first-class local runtime** - Paperclip can configure and run `grok_local` through the built-in adapter registry, with server, UI, CLI, transcript parsing, session handling, diagnostics, and focused adapter coverage. ([#6087](https://github.com/paperclipai/paperclip/pull/6087), @devinfoley) - **Issue documents can be locked for safer handoffs** - Board-managed document locks preserve approved snapshots, route agent wri | High | 5/17/2026 |
| v2026.512.0 | # v2026.512.0 > Released: 2026-05-12 ## Highlights - **Planning mode for issue work** â Issues now carry a `standard` / `planning` work mode across the database, validators, server flows, plugin protocol, adapter heartbeat payloads, and board UI. Operators can create planning-mode issues, see them clearly in rows and detail composers, and have the mode preserved through suggested follow-up issues. ([#5353](https://github.com/paperclipai/paperclip/pull/5353)) - **Full company search** â A new | High | 5/12/2026 |
| v2026.428.0 | # v2026.428.0 > Released: 2026-04-28 ## Highlights - **Pause and resume agents from the sidebar** â The agent sidebar now exposes per-agent edit, pause, and resume actions through a hover/focus action menu, with toast feedback and per-agent pending state. Budget-paused agents are surfaced clearly and intentionally require a non-sidebar path to resume. ([#4616](https://github.com/paperclipai/paperclip/pull/4616)) - **Long issue threads stay smooth** â Issue chat threads now virtualize their ro | High | 4/28/2026 |
| v2026.427.0 | # v2026.427.0 > Released: 2026-04-27 ## Highlights - **Multi-user access and invite flows** â Paperclip can now run as a shared, authenticated control plane. Real human identities, company memberships, invite creation/landing, onboarding, profile settings, and company-scoped access controls are first-class while keeping the local-first single-operator path intact. ([#3784](https://github.com/paperclipai/paperclip/pull/3784)) - **Structured issue-thread interactions** â Agents can now post str | High | 4/27/2026 |
| 2026.416.0 | Imported from npm (2026.416.0) | Low | 4/21/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | High | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | High | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | High | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | Medium | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | Medium | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | Medium | 4/16/2026 |
| v2026.416.0 | # v2026.416.0 > Released: 2026-04-16 ## Highlights - **Issue chat thread** â Replaced the classic comment timeline with a full chat-style thread powered by assistant-ui. Agent run transcripts, chain-of-thought, and user messages now render inline as a continuous conversation with polished avatars, action bars, and relative timestamps. ([#3079](https://github.com/paperclipai/paperclip/pull/3079)) - **Execution policies** â Issues can now carry a review/approval execution policy with multi-stag | Medium | 4/16/2026 |
| v2026.403.0 | # v2026.403.0 > Released: 2026-04-03 ## Highlights - **Inbox overhaul** â New "Mine" inbox tab with mail-client keyboard shortcuts (j/k navigation, a/y archive, o open), swipe-to-archive, "Mark all as read" button, operator search with keyboard controls, and a "Today" divider. Read/dismissed state now extends to all inbox item types. ([#2072](https://github.com/paperclipai/paperclip/pull/2072), [#2540](https://github.com/paperclipai/paperclip/pull/2540)) - **Feedback and evals** â Thumbs-up/d | Medium | 4/4/2026 |
| v2026.325.0 | # v2026.325.0 > Released: 2026-03-25 ## Highlights - **Company import/export** â Full company portability with a file-browser UX for importing and exporting agent companies. Includes rich frontmatter preview, nested file picker, merge-history support, GitHub shorthand refs, and CLI `company import`/`company export` commands. Imported companies open automatically after import, and heartbeat timers are disabled for imported agents by default. ([#840](https://github.com/paperclipai/paperclip/pul | Medium | 3/25/2026 |
| v2026.318.0 | # v2026.318.0 > Released: 2026-03-18 ## Highlights - **Plugin framework and SDK** â Full plugin system with runtime lifecycle management, CLI tooling, settings UI, breadcrumb and slot extensibility, domain event bridge, and a kitchen-sink example. The Plugin SDK now includes document CRUD methods and a testing harness. ([#904](https://github.com/paperclipai/paperclip/pull/904), [#910](https://github.com/paperclipai/paperclip/pull/910), [#912](https://github.com/paperclipai/paperclip/pull/912) | Low | 3/18/2026 |
| v0.3.1 | # v0.3.1 > Released: 2026-03-12 ## Highlights - **Gemini CLI adapter** â Full local adapter support for Google's Gemini CLI. Includes API-key detection, turn-limit handling, sandbox and approval modes, skill injection into `~/.gemini/`, and yolo-mode default. ([#452](https://github.com/paperclipai/paperclip/pull/452), [#656](https://github.com/paperclipai/paperclip/pull/656), @aaaaron) - **Run transcript polish** â Run transcripts render markdown, fold command stdout, redact home paths and us | Low | 3/12/2026 |
| v0.3.0 | # v0.3.0 > Released: 2026-03-09 ## Highlights - **New adapters: Cursor, OpenCode, and Pi** â Paperclip now supports three additional local coding agents. Cursor and OpenCode integrate as first-class adapters with model discovery, run-log streaming, and skill injection. Pi adds a local RPC mode with cost tracking. All three appear in the onboarding wizard alongside Claude Code and Codex. ([#62](https://github.com/paperclipai/paperclip/pull/62), [#141](https://github.com/paperclipai/paperclip/p | Low | 3/9/2026 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
More from GitHub Actions
@aaif/gooseGoose - an open-source AI agent
@n8n-as-code/skillsAI Agent skills library for n8nac (internal â use npx n8nac skills)
@zhin.js/agentZhin AI Agent â session, ZhinAgent, init; composes @zhin.js/core providers and tools
@db-ux/agent-cliCLI for DB UX Design System generate AI agent instructions
More in Frameworks
bamlThe AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
agentaThe open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
cachetoolsExtensible memoizing collections and decorators
igniterA code generation and project patching framework.