litellm-agent-platform

Name: litellm-agent-platform
Author: BerriAI

by BerriAI

Verified

Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault proxy.

540stars

58forks

TypeScript

Added 5/17/2026

View on GitHub Download ZIP Scan for vulnerabilities

30 days in the Featured rail · terms & refunds

AI Agentsagent-platformagent-vaultclaude-codecodexcodex-clilitellmlitellm-ai-gatewaysandbox

Installation

# Add to your Claude Code skills
git clone https://github.com/BerriAI/litellm-agent-platform

Getting Started

Guides for using ai agents skills like litellm-agent-platform.

Security ReportVerified

Last scanned: 5/20/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "@anthropic-ai/claude-agent-sdk: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@anthropic-ai/sdk: Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "next: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "postcss: PostCSS has XSS via Unescaped </style> in its CSS Stringify Output",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "ws: ws: Uninitialized memory disclosure",
      "severity": "medium"
    }
  ],
  "status": "PASSED",
  "scannedAt": "2026-05-20T07:43:43.391Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

LiteLLM Agent Platform

[!WARNING] Deprecation Notice:

For a unified harness across OpenCode/Claude Code/Codex, go to: lite-harness.

For a minimal Rust AI Gateway for coding agents, go to: litellm-rust

LiteLLM Agent Platform

LiteLLM Agent Platform is self-hosted infrastructure for running coding agents — Claude Code, Codex, Hermes anything — inside isolated sandboxes with a credential vault, so agents can run with bypass-permissions on without ever seeing your real keys. Use it from the lap CLI in your terminal, the web UI, or call the API directly.

Learn more in the docs.

Get started

[!NOTE] The lap CLI talks to a running instance of LiteLLM Agent Platform. To self-host the platform itself, jump to Self-hosting.

Install the lap CLI:

git clone https://github.com/BerriAI/litellm-agent-platform.git
cd litellm-agent-platform/cli && npm install
ln -sf "$PWD/bin/lap.mjs" ~/.local/bin/lap

Point it at your platform:
```
lap login
```
Open a sandbox:
```
lap claude-code-cli1
```

That spins up a fresh Kubernetes pod running Claude Code, attaches your local terminal to its TTY over a WebSocket, and drops you straight into the agent. The pod's env contains only stub credentials (e.g. GITHUB_TOKEN=stub_github_a8f1); the vault swaps them for real keys on every outbound TLS connection. Press Ctrl-D to detach; the session stays alive for 24h. See docs/lap-cli.md for the full CLI.

Demo Video

▶ Demo: setting up codex and claude-code sandboxes · ~5 min

End-to-end walkthrough: create an agent, open a sandbox from the lap CLI, attach a local terminal, run codex / claude-code inside.

Supported harnesses

Harness	Quickstart
Claude Code	docs.litellm-agent-platform.ai/quickstart/claude-code
Codex	docs.litellm-agent-platform.ai/quickstart/codex
Hermes	docs.litellm-agent-platform.ai/quickstart/hermes

Self-hosting

Sandboxes run on Kubernetes via the kubernetes-sigs/agent-sandbox CRD. Local dev uses kind.

Prereqs: Docker Desktop, kind, kubectl, helm, a LiteLLM gateway URL (or run the bundled one — see below).

bin/kind-up.sh
docker compose up

bin/kind-up.sh is idempotent — provisions a kind cluster agent-sbx, installs the agent-sandbox controller, and loads the harness image. docker compose up boots Postgres, runs the schema migration, and starts web (:3000) + worker.

Open localhost:3000 to create an agent. Then point lap at it and run through the steps above.

Self-hosted LiteLLM gateway (optional)

If you don't already have a LiteLLM proxy you can route through, the repo ships an optional compose service that runs one locally. Copy the example config, fill in your provider key(s), and bring it up alongside the platform:

cp litellm-config.yaml.example litellm-config.yaml
# Edit litellm-config.yaml to enable the models you need
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env

docker compose -f docker-compose.yml -f docker-compose.litellm.yml up

The proxy listens on :4000. Point the platform at it via .env:

# kind sandbox backend (the default self-hosting path): the harness pods run
# in the kind cluster, on a separate Docker network from this compose project,
# and reach the host-published proxy port via host.docker.internal.
LITELLM_API_BASE=http://host.docker.internal:4000
LITELLM_API_KEY=sk-litellm-local-master  # must match master_key in litellm-config.yaml

[!NOTE] LITELLM_API_BASE is injected into the sandbox harness pods, not just the compose web/worker containers. With the kind backend, use http://host.docker.internal:4000 — the pods live on the kind Docker network and cannot resolve the litellm compose service name. Only if you run without kind (e.g. LOCAL_SANDBOX_URL or the brain-inline harness, where everything stays inside this compose project) can you use the more direct http://litellm:4000.

Architecture and tuning: docs/k8s-backend.md.

Deploying to production

Recommended path: AWS EKS for the sandbox cluster, Render for web + worker. See deploy/ — bin/eks-up.sh provisions the cluster, the Render Blueprint at the top of deploy/render/README.md is one click.

Architecture

Developer API

Create an agent, open a session, send a message, read the reply — directly with curl. See docs/spawn-task-agent.md and src/server/DEVELOPER.md.

License

MIT — see LICENSE.

Frequently Asked Questions

What is litellm-agent-platform?

litellm-agent-platform is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by BerriAI. Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault proxy. It has 540 GitHub stars.

Is litellm-agent-platform safe to use?

Yes. litellm-agent-platform passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install litellm-agent-platform?

Clone the repository with "git clone https://github.com/BerriAI/litellm-agent-platform" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is litellm-agent-platform written in?

litellm-agent-platform is primarily written in TypeScript. It is open-source under BerriAI on GitHub, so you can review or fork the full source.

Are there alternatives to litellm-agent-platform?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh litellm-agent-platform against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

20,863

Shell

AI Agentsaibrainstorming

View details

Compare

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

224,269

34,324

JavaScript

AI Agentsai-agentsanthropic

The agent that grows with you

206,702

37,411

Python

AI Agentsaiai-agent

View details

Compare

everything-claude-code

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,940

28,768

JavaScript

AI Agentsai-agentsanthropic

View details

Compare

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,031

19,897

Shell

AI Agents

View details

Compare

gstack

by garrytan

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

112,329

16,695

TypeScript

AI AgentsSKILL.md

View details

Compare

Browse all AI Agents skills

haiku.rag MakeMoneyWithAI

LiteLLM Agent Platform

[!WARNING] Deprecation Notice:

For a unified harness across OpenCode/Claude Code/Codex, go to: lite-harness.

For a minimal Rust AI Gateway for coding agents, go to: litellm-rust

LiteLLM Agent Platform

Learn more in the docs.

Get started

[!NOTE] The lap CLI talks to a running instance of LiteLLM Agent Platform. To self-host the platform itself, jump to Self-hosting.

Install the lap CLI:

git clone https://github.com/BerriAI/litellm-agent-platform.git
cd litellm-agent-platform/cli && npm install
ln -sf "$PWD/bin/lap.mjs" ~/.local/bin/lap

Point it at your platform:
```
lap login
```
Open a sandbox:
```
lap claude-code-cli1
```

Demo Video

▶ Demo: setting up codex and claude-code sandboxes · ~5 min

End-to-end walkthrough: create an agent, open a sandbox from the lap CLI, attach a local terminal, run codex / claude-code inside.

Supported harnesses

Harness	Quickstart
Claude Code	docs.litellm-agent-platform.ai/quickstart/claude-code
Codex	docs.litellm-agent-platform.ai/quickstart/codex
Hermes	docs.litellm-agent-platform.ai/quickstart/hermes

Self-hosting

Sandboxes run on Kubernetes via the kubernetes-sigs/agent-sandbox CRD. Local dev uses kind.

Prereqs: Docker Desktop, kind, kubectl, helm, a LiteLLM gateway URL (or run the bundled one — see below).

bin/kind-up.sh
docker compose up

Open localhost:3000 to create an agent. Then point lap at it and run through the steps above.

Self-hosted LiteLLM gateway (optional)

cp litellm-config.yaml.example litellm-config.yaml
# Edit litellm-config.yaml to enable the models you need
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env

docker compose -f docker-compose.yml -f docker-compose.litellm.yml up

The proxy listens on :4000. Point the platform at it via .env:

# kind sandbox backend (the default self-hosting path): the harness pods run
# in the kind cluster, on a separate Docker network from this compose project,
# and reach the host-published proxy port via host.docker.internal.
LITELLM_API_BASE=http://host.docker.internal:4000
LITELLM_API_KEY=sk-litellm-local-master  # must match master_key in litellm-config.yaml

[!NOTE] LITELLM_API_BASE is injected into the sandbox harness pods, not just the compose web/worker containers. With the kind backend, use http://host.docker.internal:4000 — the pods live on the kind Docker network and cannot resolve the litellm compose service name. Only if you run without kind (e.g. LOCAL_SANDBOX_URL or the brain-inline harness, where everything stays inside this compose project) can you use the more direct http://litellm:4000.

Architecture and tuning: docs/k8s-backend.md.

Deploying to production

Architecture

Developer API

Create an agent, open a session, send a message, read the reply — directly with curl. See docs/spawn-task-agent.md and src/server/DEVELOPER.md.

License

MIT — see LICENSE.