10 posts tagged with "agents"

You've built an agent with your own tools, prompts, and model configuration. Now you want to try a different harness on the same task.

LiteAgents lets you switch agent harnesses without rewriting your application. Its interface is modeled after the Claude Agent SDK, including the query() pattern and typed messages. Choose Deep Agents, Pydantic AI, Claude Agent SDK, Codex, or OpenCode while keeping your tools, MCP connections, model configuration, and client code. Each selected harness runs its own agent loop.

LiteLLM gives you a common interface to models. LiteAgents brings that approach to agent harnesses, with native controls and optional durability through Temporal.

An engineer asks for an API key for a new project. You need to choose its models, set a budget, and assign it to a team. As usage grows, you need to check spending and adjust those limits.

LiteAdmin MCP lets your agent handle these tasks through your gateway's management API. Connect it to an MCP client or a custom agent. We built LiteAdmin, our Slack admin agent, on the same connector.

A bot looks up the weather, then checks a shop's opening hours. The user asks, "What time does the shop close?" The bot still sends the old weather report to the model, even though it no longer helps answer the question.

TypeSafe Jev helps LiteLLM spot tool results that are no longer needed. LiteLLM replaces those results with a short notice before calling the model. This is called compaction, and it can reduce the input tokens used by long conversations.

Shared agents can preserve individual identity, access, and spend controls.

When a finance agent serves multiple business units, platform teams need a consistent way to identify who initiated each request, apply the right model and tool permissions, and attribute spend. LiteLLM keeps this context available across shared-agent workflows so each business unit can operate under its own access and budget policies.

LiteLLM provides one control plane for this workflow across the Agent Gateway, Model Gateway, and MCP Gateway. Teams can share the same agent infrastructure while keeping access, credentials, spend, and audit data tied to the right caller.

The OpenAI Responses and Chat Completions APIs let you declare a code_interpreter tool and the model runs Python inside an OpenAI-hosted container. That container is opaque, billed by OpenAI, and the code (often customer data) leaves your perimeter. LiteLLM now let's you intercept that tool call and runs it in a sandbox you control. The client request is unchanged.

Available starting LiteLLM v1.91.0.dev1. Check here for releases.

Last updated: June 2026

Agent infrastructure is already separating into three layers: models, harnesses, and runtimes. We believe a fourth layer will emerge: the unified agent control plane. This will allow calling agents living in different agent runtimes, all from 1 place.

Harnesses are the next frontier of vendor lock-in. LiteLLM was built to swap across model providers easily. However, as the models get saturated, the next area for competition becomes the harnesses and managed agents. To make it easy to go across vendors at the harness layer, we're launching the Lite-Harness SDK. This is a simple TypeScript+Python SDK which allows developers to change harnesses, like they change models.

Our goal was to 10x the productivity of our company with agents.

Three weeks ago we began building an agent that could own 30% of our engineering tickets. Here's what we've learnt so far.

Thank you to everyone who joined our May town hall.

We covered security hardening, release versioning changes, new product launches (MCP toolsets, on-behalf-of OAuth), performance wins, and our biggest bet yet, the LiteLLM Agent Platform.

We're introducing the LiteLLM Managed Agents Platform - a simple, self-hosted infrastructure platform for running multiple agents in production.