Software Agent SDK

The Faheem Code SDK is a set of Python and REST APIs for building agents that work with code.

You can use the Faheem Code SDK for:

One-off tasks, like building a README for your repo
Routine maintenance tasks, like updating dependencies
Major tasks that involve multiple agents, like refactors and rewrites
OpenAI-compatible access to an Faheem Code agent from chat UIs, IDEs, voice platforms, and other clients

You can even use the SDK to build new developer experiences—it’s the engine behind the Faheem Code CLI and Faheem Code Cloud.

Get started with some examples or keep reading to learn more.

Features

Single Python API

A unified Python API that enables you to run agents locally or in the cloud, define custom agent behaviors, and create custom tools.

Pre-defined tools

Ready-to-use tools for executing Bash commands, editing files, browsing the web, integrating with MCP, and more.

REST-based agent server

A production-ready server that runs agents anywhere, including Docker and Kubernetes, while connecting seamlessly to the Python API.

OpenAI-compatible endpoint

Access the Faheem Code agent via an OpenAI-compatible endpoint for chat UIs, IDEs, voice platforms, and other OpenAI-style clients.

Why Faheem Code SDK?

Emphasis on coding

While other agent SDKs (e.g. LangChain) are focused on more general use cases, like delivering chat-based support or automating back-office tasks, Faheem Code is purpose-built for software engineering.

While some folks do use Faheem Code to solve more general tasks (code is a powerful tool.), most of us use Faheem Code to work with code.

State-of-the-art performance

Faheem Code is a top performer across a wide variety of benchmarks, including SWE-bench, SWT-bench, and multi-SWE-bench. The SDK includes a number of state-of-the-art agentic features developed by our research team, including:

Task planning and decomposition
Automatic context compression
Security analysis
Strong agent-computer interfaces

Model agnostic

The SDK works with any LLM reachable through LiteLLM, including hosted models such as Claude and GPT and open-weight models such as Qwen and Devstral. Some other agent SDKs bind you to one provider; models move quickly, so staying provider-neutral keeps your options open.