Tomte

Tomte is a Go toolkit for building small, single-task AI agents that run on a schedule or on demand.

Tomte is a Go toolkit for building small agents that do one specific job on a schedule or when asked. Each agent compiles into a single small binary of about 6 MB that uses roughly 11 MB of memory while waiting. Tools, jobs, and commands are written as Go functions with configuration in Go code instead of YAML or plugins. It supports any OpenAI-compatible API such as OpenRouter, z.ai, Groq, OpenAI, or local Ollama models. Results and failures are sent to Telegram, telekinesis, or stdout. Every run includes strict caps on steps, execution time, and dollar limits to ensure safe autonomous operation.

Tomte at a glance

Best for: Software engineer
Runs on: Linux
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: tomte.run

Key features

Compiles into a single small binary
Uses Go functions for tools and commands
Supports OpenAI-compatible APIs and Ollama
Schedules tasks with cron fields or intervals
Sends results to Telegram or stdout
Enforces strict step, time, and dollar limits
Runs with resource caps of 128 MB memory and half a CPU

Use it for

Run scheduled news digests and summaries
Chase and process unpaid invoices automatically
Execute single-task background chores in Go

Alternatives to Tomte

Letta — Provides agents with advanced memory and continual learning capabilities.
Letta Code — It features persistent memory, sleep-time compute, and git-tracked context.
FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.
Agentloop — Provides a clean agent loop with provider-agnostic LLM access, hooks, and safety budgets.
APIStack — Connect AI agents to over 100 tools using one API key or a single MCP endpoint.
Comma — It operates 24/7 on a cloud computer to finish tasks independently.
LiteLLM Agent Control Plane — Provides a single API to call all your agents across different runtimes.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
thClaws — Runs locally in native Rust with zero cloud lock-in and multi-provider support.
Waku Agent — Local-first memory storage and readable Python code for AI agent logic.
LLMStack — Builds AI applications and agents with custom data without writing code.

All Tomte alternatives