StartupHakk/OpenMonoAgent.ai · 1.8K Stars · GitHub 趋势

📦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.

⚖️ NOASSERTION📅 创建于 2026-04-30🔄 更新于 2026-10-27

🔗 GitHub C#

📄 仓库 README

在 GitHub 查看 ↗

来自 GitHub 仓库自述文件 · 版权归原作者所有

Open-source coding agent. Local-first. Zero cost. Zero cloud.
_{Built to democratize AI. Powered by .NET.}

Quickstart · Free OMA Course · What's shipping · How it compares · What's inside · Hardware · Docs · Roadmap · Contributing

OpenMono is a coding agent that runs entirely on your hardware — no subscriptions, no data leaving your network, no per-token billing. It pairs a .NET 10 CLI with its own llama.cpp inference server, giving you a full agentic loop with 21 built-in tools, Docker sandboxing, and deep code intelligence. NVIDIA GPU, AMD APU (integrated Radeon iGPU, unified memory), or Apple Silicon (Metal) — it auto-configures itself. You own the model, the compute, and the data.

Free Course — Get Started with OMA

_{Need help? Contact us — we'll help you get set up.}

Quickstart

One command. Auto-detects GPU · APU/iGPU · Apple Silicon. Installs model, runtime, and Docker containers.

bash <(curl -fsSL https://raw.githubusercontent.com/StartupHakk/OpenMonoAgent.ai/refs/heads/main/get-openmono.sh)

Then from any project:

openmono agent            # TUI mode (default)
openmono agent --classic  # classic scrolling terminal

_{→ Full command reference — daily commands, setup flags, GPU/iGPU options · Need help? Book a call}

What's shipping

_{Get them: openmono setup search · OPENMONO_VISION_ENABLED=1 · App Store · Google Play · VS Code Marketplace}

How it compares

Most coding agents are cloud products wearing an open-source label. Your prompts, your code, and your context hit someone else's servers on every keystroke. OpenMono runs the model on your hardware — after the one-time setup, inference costs nothing. Your code never leaves the machine. No account. No usage dashboard. No API key.

How OpenMono compares to Claude Code and OpenCode across cost, privacy, inference, sandboxing, code intelligence, extensibility, MCP, UI, and hardware

→ Full architecture + diagram · 5 provider backends · runs at ~45 tok/s on GPU, ~20 tok/s on AMD iGPU (APU)

What's inside

01 · Bundled inference — zero config, zero cost llama.cpp ships inside Docker. Installer detects your hardware and picks the right model. After setup, every token is free. `GPU` Qwen3.8-27B dense · ~60 tok/s `iGPU` Qwen3.6-35B-A3B MoE · APU unified memory · ~20 tok/s `Mac` Qwen3.6-35B-A3B MoE · Metal · ~45–48 tok/s → [Models & reasoning mode](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md)	02 · Agentic loop that earns its name Up to 1,000 iterations per turn. Doom-loop detection nudges on repeated tool batches, escalates the nudge at 3 consecutive detections, and ends the turn at 5. Checkpoints at 65% context fill, compacts at 80%. Runs until done — then stops.
03 · [21 tools](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/ARCHITECTURE.md), guarded pipeline Every call: parse → schema validate → path sanity → plan-mode gate → host-mode gate → permission check → cache → pre-hook → execute → post-hook → artifact store → cache write → invalidate. Read-only tools run in parallel. Nothing bypasses the pipeline.	04 · 5 specialist sub-agents Isolated sessions with locked tool sets and turn budgets: `Explore` · read-only discovery · 100 turns `Plan` · architecture, no writes · 100 turns `Coder` · full file access · 300 turns `Verify` · adversarial + Roslyn · 150 turns `general-purpose` · everything · 200 turns
05 · Docker sandbox In sandbox mode the project mounts as `/workspace`. The agent reads and writes your real files — that's the blast radius; nothing outside that mount is visible. Host mode is the explicit exception: machine-level actions run only through approved `HostExec` calls.	06 · Deep code intelligence Roslyn: type hierarchy, blast-radius, cross-file symbol search, callers, diagnostics — 5-min compilation cache. LSP for TypeScript, Python, Go, Rust, lazy-started on first use. Auto-detects [graphify](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/graphify.md) (semantic concept graph, 25+ languages) and [code-review-graph](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/code-review-graph.md) (structural call graph via MCP, ~22 tools) if installed — no config needed.
07 · [Playbooks](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/PLAYBOOKS.md) YAML workflows with typed parameters, conditional gates, and checkpoint/resume.	08 · [5 provider backends](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md) Local llama.cpp is the default; Strata is the supported Linux high-end backend. OpenAI, Anthropic, and Ollama are available but WIP — see [Models](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md) for details. Providers are selected in `settings.json` at startup; `/model` switches the model on the active provider.
09 · Distributed inference Agent on your laptop, inference on a separate GPU machine. No port forwarding — tunnel is established outbound from the inference box. Free relay at [app.openmonoagent.ai](https://app.openmonoagent.ai). → [Dual-box setup guide](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#dual-box-setup)	10 · Vision Attach images in chat with `@screenshot.png` or ask the agent to read any image file. The multimodal projector (mmproj) is downloaded automatically at setup. Supported formats: PNG, JPG, GIF, WebP. Large images are auto-resized to fit within the image budget. Enable vision in `settings.json` (`inference.vision_enabled`) or set `OPENMONO_VISION_ENABLED=1`. → [Vision setup & usage](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#vision)
11 · Private web search & scraping Self-hosted search via SearXNG — your queries never leave the machine. Anti-bot scraping via Scrapling + Camoufox (real browser, Cloudflare bypass). Single Caddy gateway, auto-detected. Falls back to DuckDuckGo / direct fetch when the gateway is absent. `openmono setup search` · `openmono setup scraper` → [Web services architecture](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/ARCHITECTURE.md#inference-side-web-services-caddy-gateway)	12 · VS Code extension The full agent loop in your editor sidebar — streaming responses, live Markdown, file edits, bash, and permission prompts without leaving VS Code. Connects to the local agent over ACP on port `7475`. Also works in Cursor. `code --install-extension StartupHakk.openmono-agent` → [Extension docs](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#vs-code--cursor-extension) · [Marketplace](https://marketplace.visualstudio.com/items?itemName=StartupHakk.openmono-agent)

Distributed inference: agent on laptop, inference on GPU machine

Supported Hardware

Linux — NVIDIA GPU and AMD iGPU: the auto-selected model, context size, and speed for each VRAM and RAM configuration

macOS — Apple Silicon (Metal): the auto-selected model, context size, and speed for each unified-memory size

_{Setup auto-detects GPU · iGPU/APU · no config needed and picks the best model your hardware can run — no prompts. Pass --options to choose the model, vision, and parallel slots yourself, or --model=<name> to pin one. The pick depends on VRAM and system RAM: on Linux a 24 GB+ card gets Qwen3.8-Flash-Next (Strata) on a 48 GB-class box and Qwen3.8-27B below that, a 16 GB card keeps Qwen3.8-27B, a 12 GB card and AMD 780M iGPUs (32 GB+ RAM) get Ternary-Bonsai-2-27B via Prism. Requires Ubuntu 26.04 LTS (recommended) or 25.10. On macOS, the full and inference roles require Apple Silicon (M1+); 48 GB+ unified memory is the recommended, tested configuration. 24–47 GB and 16–23 GB Macs run Ternary-Bonsai (PQ2_0 / PTQ1_0) with a tighter context window. Intel Macs: agent-only mode. macOS 14+ (Sonoma/Sequoia) recommended.}

Need Help?

Stuck on setup, or want OpenMono on your own servers? We install and support private OpenMono deployments — contact us, book a call, and we'll walk you through getting it running on your hardware. Pick your hardware. We handle the rest.

Docs

`Roadmap`	_{What's next}
`Setup & commands`	_{Daily commands, TUI vs classic, flags}
`Deployment modes`	_{Single-box vs split-box, server-ops runbook}
`Architecture`	_{.NET CLI + llama.cpp + Docker, full diagram}
`Models & reasoning`	_{Model tiers, reasoning mode, provider config}
`Configuration`	_{settings.json, providers, permissions, MCP servers}
`Playbooks`	_{YAML workflows, typed params, checkpoint/resume}
`graphify`	_{Semantic code graph, 25+ languages}
`code-review-graph`	_{Structural call graph via MCP}
`VS Code extension`	_{Chat panel for VS Code 1.85+ · also works in Cursor · Marketplace}
`Contributing`	_{How to contribute}

PUBLIC BETA _{Early access is open — we're shipping updates fast. Try it out and tell us what you'd like to see next.}

Contributing

_{OpenMono is early and moving fast. Contributions are welcome — new tools, providers, LSP servers, playbooks, bug fixes, or docs.}

→ Read the contributing guide before opening a PR

"AI shouldn't be a subscription you rent. It should be infrastructure you own —
sitting on your desk, serving your code, answering only to you."

_{— Startup Hakk}

Need Help? · Contributing

📈 近 7 天 Star 趋势

每日新增 Star（柱）与累计 Star（线）· 数据来自 GitHub

🏆 排名变化趋势

在各榜单中的排名历史（数字越小越靠前）

📋 历史上榜记录

每次快照的详细数据

日期	榜单	排名	周期新增	总 STAR

01 · Bundled inference — zero config, zero cost llama.cpp ships inside Docker. Installer detects your hardware and picks the right model. After setup, every token is free. `GPU` Qwen3.8-27B dense · ~60 tok/s `iGPU` Qwen3.6-35B-A3B MoE · APU unified memory · ~20 tok/s `Mac` Qwen3.6-35B-A3B MoE · Metal · ~45–48 tok/s → [Models & reasoning mode](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md)	02 · Agentic loop that earns its name Up to 1,000 iterations per turn. Doom-loop detection nudges on repeated tool batches, escalates the nudge at 3 consecutive detections, and ends the turn at 5. Checkpoints at 65% context fill, compacts at 80%. Runs until done — then stops.
03 · [21 tools](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/ARCHITECTURE.md), guarded pipeline Every call: parse → schema validate → path sanity → plan-mode gate → host-mode gate → permission check → cache → pre-hook → execute → post-hook → artifact store → cache write → invalidate. Read-only tools run in parallel. Nothing bypasses the pipeline.	04 · 5 specialist sub-agents Isolated sessions with locked tool sets and turn budgets: `Explore` · read-only discovery · 100 turns `Plan` · architecture, no writes · 100 turns `Coder` · full file access · 300 turns `Verify` · adversarial + Roslyn · 150 turns `general-purpose` · everything · 200 turns
05 · Docker sandbox In sandbox mode the project mounts as `/workspace`. The agent reads and writes your real files — that's the blast radius; nothing outside that mount is visible. Host mode is the explicit exception: machine-level actions run only through approved `HostExec` calls.	06 · Deep code intelligence Roslyn: type hierarchy, blast-radius, cross-file symbol search, callers, diagnostics — 5-min compilation cache. LSP for TypeScript, Python, Go, Rust, lazy-started on first use. Auto-detects [graphify](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/graphify.md) (semantic concept graph, 25+ languages) and [code-review-graph](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/code-review-graph.md) (structural call graph via MCP, ~22 tools) if installed — no config needed.
07 · [Playbooks](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/PLAYBOOKS.md) YAML workflows with typed parameters, conditional gates, and checkpoint/resume.	08 · [5 provider backends](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md) Local llama.cpp is the default; Strata is the supported Linux high-end backend. OpenAI, Anthropic, and Ollama are available but WIP — see [Models](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/MODELS.md) for details. Providers are selected in `settings.json` at startup; `/model` switches the model on the active provider.
09 · Distributed inference Agent on your laptop, inference on a separate GPU machine. No port forwarding — tunnel is established outbound from the inference box. Free relay at [app.openmonoagent.ai](https://app.openmonoagent.ai). → [Dual-box setup guide](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#dual-box-setup)	10 · Vision Attach images in chat with `@screenshot.png` or ask the agent to read any image file. The multimodal projector (mmproj) is downloaded automatically at setup. Supported formats: PNG, JPG, GIF, WebP. Large images are auto-resized to fit within the image budget. Enable vision in `settings.json` (`inference.vision_enabled`) or set `OPENMONO_VISION_ENABLED=1`. → [Vision setup & usage](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#vision)
11 · Private web search & scraping Self-hosted search via SearXNG — your queries never leave the machine. Anti-bot scraping via Scrapling + Camoufox (real browser, Cloudflare bypass). Single Caddy gateway, auto-detected. Falls back to DuckDuckGo / direct fetch when the gateway is absent. `openmono setup search` · `openmono setup scraper` → [Web services architecture](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/ARCHITECTURE.md#inference-side-web-services-caddy-gateway)	12 · VS Code extension The full agent loop in your editor sidebar — streaming responses, live Markdown, file edits, bash, and permission prompts without leaving VS Code. Connects to the local agent over ACP on port `7475`. Also works in Cursor. `code --install-extension StartupHakk.openmono-agent` → [Extension docs](https://github.com/StartupHakk/OpenMonoAgent.ai/blob/HEAD/docs/SETUP.md#vs-code--cursor-extension) · [Marketplace](https://marketplace.visualstudio.com/items?itemName=StartupHakk.openmono-agent)