Skip to content
Back to search

lemma-platform

Multiplayer harness that shapes around your work. Agents, apps and workflows your team shares, used from Slack, Telegram, WhatsApp, Teams, Email, Web or your own AI agent.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/lemma-work/lemma-platform with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/lemma-work/lemma-platform'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lemma-work--lemma-platform/badge.svg)](/listings/lemma-work--lemma-platform)

HTML

<a href="/listings/lemma-work--lemma-platform"><img src="/api/listings/lemma-work--lemma-platform/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

Lemma Cloud

The same stack, hosted, reachable by teammates and surfaces:

uv tool install lemma-terminal
lemma servers select lemma-cloud
lemma auth login
lemma skills install
lemma pod create support-ops --with-starter   # scaffolds a working starter (table + agent) and imports it
lemma chat "what can you do in this pod?"

Your laptop

Download Lemma Desktop, choose **Local**, and select **Install local services**. Lemma owns the local runtime and picks its own ports, so one bootstrap command reads them back out of Desktop and registers them with the CLI as the `local` server.

That link opens the version-tagged release: the build to install, and the one Desktop's updater follows. The `desktop-nightly-<sha>` entries above it on the Releases page are prereleases built from a branch to try an unreleased change.

Run this after Desktop's local setup has finished once:

uv tool install lemma-terminal
curl -fsSL https://raw.githubusercontent.com/lemma-work/lemma-platform/main/install.sh |
  bash -s -- --cli-only          # registers Desktop's endpoints as the local server
lemma servers select local
lemma auth login
lemma skills install
lemma pod create support-ops --with-starter

Then open the generated `support-ops/` directory in the coding agent you already use and describe the system you want. Full Desktop, Agent Host, and provider setup lives in [Install in depth](#install-in-depth) and [docs/installation.md](docs/installation.md).

Use `uv tool install`, not `pip`. `lemma-terminal` needs Python 3.14, and `uv tool install` provisions that interpreter itself, so whatever `python3` is on your machine does not matter. `pip install lemma-terminal` on an older interpreter does not fail — it quietly resolves back to `0.6.2`, the last release that allowed 3.11, and installs a CLI several minors behind the server. `lemma --version` reports what you actually have.

**If a command did not do what it says here:**

| Symptom | What to do | | --- | --- | | `Server not found: local` | Desktop's local setup has not run, or the bootstrap above was skipped. Run it, then `lemma servers show` to confirm which server is active. | | Agents unavailable, or chat answers with a provider error | No AI provider has validated yet. **Local Control Center → AI Providers**; Ollama or LM Studio if you have no API key. | | Something works in the app but not in the CLI, or the other way round | `lemma doctor` — it diagnoses client/server version skew and duplicate installs. |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 173 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="lemma-frontend/src/app/icon.svg" alt="Lemma" width="56">
  3. # Lemma
  4. **A multiplayer harness that shapes itself around your work.**
  5. Your people meet it as a teammate: give it a job, share it with everyone, and teach it as you go.
  6. <a href="https://lemma.work"><img src="https://img.shields.io/badge/Try_it_free-5a3fd4?style=for-the-badge" alt="Try Lemma free"></a>
  7. <a href="https://lemma.work/download"><img src="https://img.shields.io/badge/Download_for_macOS-141414?style=for-the-badge&logo=apple&logoColor=white" alt="Download Lemma for macOS"></a>
  8. [Docs](https://lemma.work/docs) · [Discord](https://discord.gg/x2NVyNPQR) · [Templates](https://lemma.work/templates)
  9. </div>
  10. <br>
  11. <picture>
  12. <source media="(prefers-color-scheme: dark)" srcset="docs/Assets/hero-dark.svg">
  13. <img src="docs/Assets/hero-light.svg" alt="A teammate's space in Lemma: its apps, context and workflows, the people who share it, the agent at work, and the places people ask it from." width="100%">
  14. </picture>
  15. It runs on the Claude Code or Codex subscription you already pay for, Lemma's hosted models, or any OpenAI- or Anthropic-compatible key.
  16. ## Get started
  17. **Lemma Cloud.** Sign up at [lemma.work](https://lemma.work). Nothing to install.
  18. **On your Mac.** [Download Lemma](https://lemma.work/download), open it, and choose
  19. **Local**. It installs everything it needs and runs on your machine. See
  20. [installation](docs/installation.md) if something doesn't start.
  21. **On your own server.** Bring up the whole stack on a VM you control, with
  22. HTTPS. See [self-hosting](docs/self-hosting.md).
  23. ```bash
  24. git clone https://github.com/lemma-work/lemma-platform.git
  25. cd lemma-platform/deploy/compose && ./bootstrap.sh
  26. # add your model provider key to .env, then:
  27. docker compose up -d
  28. ```
  29. **Your coding agent.**
  30. <img src="docs/Assets/Logos/claude.svg" height="16" alt="Claude Code">&nbsp;Claude Code,
  31. <img src="docs/Assets/Logos/codex.svg" height="16" alt="Codex">&nbsp;Codex,
  32. <img src="docs/Assets/Logos/cursor.svg" height="16" alt="Cursor">&nbsp;Cursor,
  33. <img src="docs/Assets/Logos/opencode-logo-light.svg" height="16" alt="OpenCode">&nbsp;OpenCode or
  34. <img src="docs/Assets/Logos/antigravity.png" height="16" alt="Antigravity">&nbsp;Antigravity
  35. can build a whole teammate. Paste this in:
  36. ```text
  37. Set up Lemma, then build me a teammate.
  38. 1. Install the CLI with `uv tool install lemma-terminal` (not pip; it needs
  39. Python 3.14 and uv provides it).
  40. 2. Run `lemma auth login` and let me finish signing in.
  41. 3. Run `lemma skills install`, then tell me to restart you so the skills load.
  42. 4. After the restart, use the Lemma builder skills.
  43. Based on what you already know about me, my work and how my team works,
  44. propose the one teammate that would take the most off our plate: its job,
  45. who it works with, and what it should never do without asking. Ask me
  46. anything you can't work out. Once I agree, build it: the tables that hold
  47. the shared state, the agents and workflows that move the work, the app
  48. people open, and the permissions, with a person approving anything
  49. consequential.
  50. ```
  51. It writes everything as files, imports them, and runs the workflow to check it
  52. stops where it should.
  53. ## Inside a teammate
  54. Each teammate lives in a **pod**: the boundary around one job. A pod holds its
  55. own agents, apps, tables, files and workflows, decides who is inside and what
  56. each person and agent can touch, and nothing crosses it unless you connect it.
  57. It exports as a folder of files, so you can version it, share it, or import it
  58. somewhere else.
  59. ## <img src="docs/Assets/icons/agents.svg" width="26" height="26" align="top" alt=""> Agents
  60. An agent is a role: a model, an instruction, and the tools, tables and
  61. connectors it is allowed to use. It answers when someone asks, and it also runs
  62. without being asked, on a schedule, when a row in a table changes, or when a
  63. webhook arrives from Slack, GitHub or anywhere else. Each run is recorded step
  64. by step, so you can see what it read, what it called, and where it stopped.
  65. Before anything consequential, like sending an email, issuing a refund or
  66. deleting a record, it pauses and asks the person who owns that decision. The run
  67. waits, for days if it has to, and carries on when they answer.
  68. ## <img src="docs/Assets/icons/apps.svg" width="26" height="26" align="top" alt=""> Apps
  69. A lot of work needs a screen rather than a chat thread: a queue to clear, a
  70. board to move, a form to fill in. Ask the teammate for one and it builds a web
  71. app, deployed at its own URL, that reads and writes the same tables its agents
  72. use. When an agent updates a record, the app is already showing it.
  73. Apps are built on the TypeScript SDK, so a developer can open the code, change
  74. it, and redeploy with `lemma apps deploy`.
  75. ## <img src="docs/Assets/icons/people.svg" width="26" height="26" align="top" alt=""> People
  76. A teammate is shared by the whole team, and each person has their own account
  77. and role inside it. One permission model covers people and agents alike: which
  78. tables they can read or write, which rows they can see, and which steps need
  79. their approval. Clients and guests are invited the same way and see only their
  80. part.
  81. Every action lands in one history: who asked, which agent ran, and what changed.
  82. ## <img src="docs/Assets/icons/context.svg" width="26" height="26" align="top" alt=""> Context
  83. The teammate keeps its memory as Markdown notes. Shared notes are readable by
  84. everyone on the team; personal notes only by you. Correct it once ("refunds over
  85. $500 go to Sam") and it writes that down and works that way from then on. Any
  86. note can be opened, read and fixed by hand.
  87. Alongside the notes are tables, typed records with row-level security, and
  88. files, the documents and PDFs agents can search. All three are read at run time,
  89. so what the teammate knows is what your team can see and edit.
  90. ## <img src="docs/Assets/icons/surfaces.svg" width="26" height="26" align="top" alt=""> Surfaces
  91. People reach the same teammate from Slack, Microsoft Teams, WhatsApp, Telegram
  92. and email. Each surface works out who is writing, matches them to their account,
  93. and applies their permissions, so a question in a Slack thread gets the same
  94. answer it would get in the app. Every agent also has its own email address that
  95. anyone can write to.
  96. Approvals travel too: a workflow waiting on someone can ask them in the chat
  97. they already use.
  98. ## <img src="docs/Assets/icons/workflows.svg" width="26" height="26" align="top" alt=""> Workflows
  99. When work passes between people and agents in the same order every time, write
  100. it down as a workflow. Each step is an agent, a function (plain code that does
  101. the same thing every time), a decision, a loop, a wait, or a form for a named
  102. person. A workflow starts on a schedule, a table change, a webhook, or by hand.
  103. Runs are durable. A step waiting on a person can wait for days, and the run
  104. resumes exactly where it stopped.
  105. ## Open source
  106. The core is [AGPLv3](LICENSE); the SDKs, CLI and skills are
  107. [Apache-2.0](LICENSES/Apache-2.0.txt). Run it on your laptop, your own server,
  108. or Lemma Cloud. To work on Lemma itself, start with
  109. [CONTRIBUTING.md](CONTRIBUTING.md) and [ARCHITECTURE.md](ARCHITECTURE.md).
  110. Questions go in [Discussions](https://github.com/lemma-work/lemma-platform/discussions)
  111. or [Discord](https://discord.gg/x2NVyNPQR).
  112. <br>
  113. <div align="center">
  114. <img src="lemma-frontend/public/teammates/cast/bolt-sm.webp" width="56" alt="Bolt">
  115. <img src="lemma-frontend/public/teammates/cast/moon-sm.webp" width="56" alt="Moon">
  116. <img src="lemma-frontend/public/teammates/cast/bloom-sm.webp" width="56" alt="Bloom">
  117. <img src="lemma-frontend/public/teammates/cast/kite-sm.webp" width="56" alt="Kite">
  118. <img src="lemma-frontend/public/teammates/cast/gem-sm.webp" width="56" alt="Gem">
  119. <img src="lemma-frontend/public/teammates/cast/spark-sm.webp" width="56" alt="Spark">
  120. <img src="lemma-frontend/public/teammates/cast/cloud-sm.webp" width="56" alt="Cloud">
  121. <img src="lemma-frontend/public/teammates/cast/prism-sm.webp" width="56" alt="Prism">
  122. <img src="lemma-frontend/public/teammates/cast/knot-sm.webp" width="56" alt="Knot">
  123. <img src="lemma-frontend/public/teammates/cast/peak-sm.webp" width="56" alt="Peak">
  124. <sub>© 2026 Folks and Machines, Inc.</sub>
  125. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.