Haskell Agent documentation

Haskell Agent is an independent agent harness that connects language models to your projects, tools, and ongoing work. Use it to investigate a codebase, implement changes, run checks, and return to a task later without starting over.

You choose the model and provider. The harness manages the conversation, tool execution, approvals, saved sessions, and parallel agents.

Start here


- Install Haskell Agent and open a project.
- Connect a provider using a supported account or API key.
- Use the terminal to give instructions, inspect progress, and review changes.

nix run --accept-flake-config github:digitallyinduced/haskell-agent

Run that command from a project directory with Nix flakes enabled. It opens the terminal client without adding an entry to your Nix profile. The first-session walkthrough takes you from installation through authentication, a small edit, review, and resuming saved work.

Your first session

Inside the agent, enter /login to connect an account, then /model to choose a model. Complete each interface before continuing. Use /session-info to inspect the selected model and current session.

Begin with investigation rather than an open-ended request to change the project. Ask the agent to identify evidence, not just offer an explanation:

Read this project's instructions and README. Identify its entry points
and the supported test command, with file references. Do not modify files.

You should receive a repository-specific explanation and see the tool activity used to establish it. If the answer names the wrong directory or invents a test command, correct that before asking for edits. Review any tool approval request against the task you actually gave.

Work on a project

Once the agent has identified the test command, give it a bounded change:

Add a short README section describing the existing test command.
Do not change application code. Run any applicable documentation checks,
report their results, and do not commit or push.

Use /diff to inspect the result. Ask for a correction if unrelated files changed, and review check output yourself before committing. /quit leaves the session; /resume lets you return later. Use project instructions and plans to establish conventions, and isolated worktrees and parallel agents when work needs to be separated.

Make it your own

For a complete worked task, start with a tutorial:


- Fix a bug: reproduce a failing test, make a bounded correction, and review the result.
- Investigate a repository: trace an entry point to its tests and produce an evidence-backed report.
- Integrate parallel changes: assign independent work, inspect each result, and validate the combined changes.
- Connect a local model: start local inference, register its model, and test generation and tool use.
- Connect an MCP server: configure a connection, authenticate, and verify a read-only operation.

Task | Guide | 

Choose a provider or connect a local model | Models | 

Resume, search, or export previous work | Sessions | 

Reuse a documented workflow | Skills | 

Connect external tools and services | MCP integrations | 

Configure code intelligence | Language servers | 

Fetch documentation with domain restrictions | Web access | 

Maintain reusable lessons across sessions | Learned skills | 

Work through a Telegram bot | Telegram | 

Dictate a prompt | Voice input | 

Control tool execution | Approvals and sandboxing | 

Find a command | Command reference | 

Diagnose a failure | Troubleshooting | 

About these guides

These guides cover the terminal client and the workflows available in this repository. Capabilities vary by model, provider, platform, and configured tools; a command's presence does not imply every provider supports every tool. Use /help inside a session for the current command list.