# StartupHakk/OpenMonoAgent.ai

(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% open source, free forever, and installed with a single command. Proudly built on C#/.NET, because AI tooling should be infrastructure, not a subscription.

Repository: https://github.com/StartupHakk/OpenMonoAgent.ai
Canonical: https://ross.abutalabs.com/products/openmonoagentai
Language: C#
License: NOASSERTION
License Family: other
Last push: 2026-08-20T00:02:51+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 8
- inputs: {"age_days": 125, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1795, forks 212 (observed 2026-08-28T04:05:37.422281+00:00)

## What it is
OpenMonoAgent is a terminal-native coding agent that runs entirely on local hardware, pairing a .NET 10 CLI with a bundled llama.cpp inference server and 20 built-in tools. It is 100% open source, free, self-hosted, and auto-configures for NVIDIA GPU, CPU, or Apple Silicon.

## Use cases
- run a coding agent locally without per-token billing
- keep code and prompts private on my own machine
- use an AI pair programmer from the terminal
- self-host an unlimited-token coding assistant
- auto-detect GPU or Apple Silicon for local LLM inference
- replace subscription AI coding tools with an open-source agent

## When to choose
- you want unlimited local AI coding help with no subscription or cloud dependency
- you have suitable hardware (NVIDIA GPU, CPU, or Apple Silicon) and value data privacy
- you prefer terminal/TUI workflows and Docker-sandboxed agent execution

## When to avoid
- you need frontier-quality model output that only large cloud models provide
- you lack the hardware to run 27B-class local models comfortably
- you need polished stability — the project is in beta with a nonstandard license (NOASSERTION/AGPL)

## Facets
- artifact type: cli-tool
- maturity: experimental
- function: agent-framework, llm-inference, cli, developer-tools
- domain: developer-tools, large-language-models
- platform: cli, self-hosted
- tags: coding-agent, local-llm, llama-cpp, dotnet, terminal-ui, privacy, self-hosted-ai, agentic-coding, ai-agents, command-line, linux, macos, docker

## Member repositories
- StartupHakk/OpenMonoAgent.ai (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.422281+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:22:50.601099+00:00, confidence not recorded.
  - readme: https://github.com/StartupHakk/OpenMonoAgent.ai (fetched 2026-08-28T04:05:37.422281+00:00, sha c43cdfd8491c)
- Data as of 2026-08-30T08:39:29.467469+00:00.