LiteLLM Agent Platform
🔥 This release made it to our blog
LiteLLM Agent Platform: Running Claude Code & Codex in Isolated Sandboxes With Vault Protection
BerriAI's LiteLLM Agent Platform is an open-source system for running coding agents in isolated Kubernetes sandboxes with credential vault protection—agents get real permissions without ever seeing your actual API keys.
### TL;DR
Self-hosted infrastructure for running coding agents — Claude Code, Codex, and any agent — inside isolated Kubernetes sandboxes with a credential vault proxy that swaps real API keys on every outbound TLS connection, so agents never see your secrets.
Key Insights & Metrics
Key Features
- Isolated Kubernetes sandboxes per agent session with 24h session persistence
- Vault proxy transparently replaces stub credentials with real API keys on every TLS connection
- lap CLI, web UI, and REST API for launching and managing coding agent sessions
→ Related Releases
MiroThinker
MiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.
Letta Code SDK
The Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.
OB-1
OB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.
AIO Sandbox
AIO Sandbox is an integrated environment designed for AI agents, combining a browser, terminal, filesystem, VSCode, Jupyter, and MCP Server into a single Docker container. This unified setup allows seamless development and execution of AI agents without the need for multiple services.
Discussion
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!