{"api_version":"1","slug":"starnet-ca2d1755","url":"https://skillsoutpost.com/agents/starnet-ca2d1755","item_type":"agent","category":"other","runs_in":["local_agent","web_service"],"os":["macos","windows"],"needs_network":null,"needs_accounts":"no","reads_files":"yes","writes_files":"yes","sends_data":"yes","access":"github","access_type":"github","at_a_glance":{"runs_in":["local_agent","web_service"],"os":["macos","windows"],"needs_network":null,"needs_accounts":"no","reads_files":"yes","writes_files":"yes","sends_data":"yes","access_type":"github","tool_type":"agent","delivery":"github","interface_type":"desktop","untrusted_creator_content":{"purpose":"A desktop harness for creating AI agents and arranging them in a pixel-art space station, with your own model key or a local Ollama model.","needs_runtime":"Node.js 18+ and Git for source runs","version":"Latest on the feat/harness-backend branch","compatibility":"According to the README: Windows 10 and 11 (64-bit) with StarNet_<version>_x64-setup.exe, macOS on Apple Silicon (M1 or later) with StarNet_<version>_aarch64.dmg, and macOS on Intel with StarNet_<version>_x64.dmg. The README says to use the native aarch64 DMG on Apple Silicon. The README describes model access through OpenRouter, sign-in with Anthropic, OpenAI or Google accounts, or local models through Ollama. The README lists agent connections to Telegram, Discord, Slack, Signal and Matrix. The README says you can attach MCP servers. The README describes importing agents from OpenClaw or Hermes. The README says Linux is not a supported public release target.","external_costs":"The README describes model access through an OpenRouter key, supported Anthropic, OpenAI or Google account sign-in, or a local Ollama model. The README's Ollama route installs Ollama and downloads a local model. The README gives no provider prices and describes local ledgers for spend, budgets and run history. Your coding agent or model provider may charge for usage.","permissions":"The README says tools operate through capability and consent checks, agents have separate workspaces and permissions, and placed station objects grant capabilities. The README describes using your OpenRouter API key or signing in with supported Anthropic, OpenAI or Google accounts, with keys held in the OS keychain. The README also describes MCP servers, key or OAuth connectors, and connections to Telegram, Discord, Slack, Signal and Matrix. The README says Night Shift continues work within an adjustable limit and logs away actions, and describes cron scheduling. The README says agent memory, transcripts, spend records, tasks and schedules persist on disk, with deliverables written to OUTBOX. The README describes importing persona, instructions, memory and model information from an existing OpenClaw or Hermes home. The README's desktop development route installs dependencies with npm ci. The top-level file list includes scripts/, whose contents the README does not describe.","usage_terms":"MIT License, as stated in the repository. See its LICENSE file for the exact terms. The README says the MIT License covers the code only. It says Andrew Sims owns the StarNet name, the logo, the station artwork and sprites, and the rest of the brand identity, and that the MIT License does not license them. It says forks and derivatives must use their own name, logo and artwork. It says third-party components remain under their original licences and points to NOTICE.md."}},"interface_type":"desktop","delivery_mode":"creator","code_host":"github","provenance":"github_index","published_at":1791761489,"rating":null,"downloads":0,"verified":null,"creator":{"login":"androoAGI","url":null},"untrusted_creator_content":{"name":"StarNet","tagline":"A desktop harness for creating AI agents and arranging them in a pixel-art space station, with your own model key or a local Ollama model.","creator_name":"androoAGI","product_version":"Latest on the feat/harness-backend branch","needs_runtime":"Node.js 18+ and Git for source runs","description":"According to the README, StarNet is a local-first desktop harness for creating agents and arranging them in a pixel-art space station. The README says the station represents live runtime state, with rooms as capability-scoped teams, hallways as handoff lanes and placed objects as capability grants.\n\nThe README describes concurrent agents with separate workspaces, transcripts, memory and bounded permissions. The README lists Telegram, Discord, Slack, Signal and Matrix connections, Night Shift, Task Briefs, OUTBOX deliverables, recipes, skills, cron schedules, MCP connectors, voice and spend ledgers.\n\nThe README describes model access through an OpenRouter key, supported Anthropic, OpenAI or Google sign-in, or a local Ollama model.","intended_users":"People who want to run several AI agents on their own computer with their own model key or a local model, and developers who want to run the harness from source.","example_tasks":"Create an agent with its own class, persona and loadout.\nRun several agents at once, each in its own workspace with bounded permissions.\nWire an agent to Telegram, Discord, Slack, Signal or Matrix.\nLeave the station running in Night Shift and review the logged away actions.\nImport an existing OpenClaw or Hermes agent from its on-disk home.","setup_instructions":"The README offers two routes. One is to download a desktop build from the StarNet releases page: StarNet_<version>_x64-setup.exe for Windows, StarNet_<version>_aarch64.dmg for Apple Silicon or StarNet_<version>_x64.dmg for Intel Macs. The other is to run from source. Clone the repository, run cd starnet, then run node sidecar/index.js. Open the local page on port 8787 and connect a provider with an OpenRouter key or a supported sign-in. For desktop development it lists npm ci, npm run desktop:dev and npm run desktop:build. INSTALL.md is the install guide. The README has the exact commands.","limitations":"According to the README, public desktop releases cover Windows 10 and 11 (64-bit), macOS on Apple Silicon and macOS on Intel. The README says Apple Silicon users should use the native aarch64 DMG because the x64 DMG runs under Rosetta 2. Linux packages are internal build artifacts, not a supported public release target. The README labels this an early release and says macOS has less real-world coverage. Source use requires Node.js 18 or newer and Git; Node.js 22 matches CI. The desktop shell also requires Rust and Tauri prerequisites. The README says local Ollama models must support tools, tasks need a large context window, and long tasks may be slower and rougher than with cloud models. The README says an 8B model takes about 10 GB of graphics memory while working. The repository can change at any time; check its README before you install.","data_handling":"The README says provider requests leave the machine when an agent runs, while station state, transcripts, memory and ledgers stay in the local StarNet workspace unless a network tool or connector is used. The README says model calls stream through the local Node sidecar and secrets are held by the sidecar and OS keychain. The README says the Ollama route connects to Ollama on the same machine. The README points to PRIVACY.md for the full data map and does not mention telemetry.","compatibility":"According to the README: Windows 10 and 11 (64-bit) with StarNet_<version>_x64-setup.exe, macOS on Apple Silicon (M1 or later) with StarNet_<version>_aarch64.dmg, and macOS on Intel with StarNet_<version>_x64.dmg. The README says to use the native aarch64 DMG on Apple Silicon. The README describes model access through OpenRouter, sign-in with Anthropic, OpenAI or Google accounts, or local models through Ollama. The README lists agent connections to Telegram, Discord, Slack, Signal and Matrix. The README says you can attach MCP servers. The README describes importing agents from OpenClaw or Hermes. The README says Linux is not a supported public release target.","external_costs":"The README describes model access through an OpenRouter key, supported Anthropic, OpenAI or Google account sign-in, or a local Ollama model. The README's Ollama route installs Ollama and downloads a local model. The README gives no provider prices and describes local ledgers for spend, budgets and run history. Your coding agent or model provider may charge for usage.","permissions":"The README says tools operate through capability and consent checks, agents have separate workspaces and permissions, and placed station objects grant capabilities. The README describes using your OpenRouter API key or signing in with supported Anthropic, OpenAI or Google accounts, with keys held in the OS keychain. The README also describes MCP servers, key or OAuth connectors, and connections to Telegram, Discord, Slack, Signal and Matrix. The README says Night Shift continues work within an adjustable limit and logs away actions, and describes cron scheduling. The README says agent memory, transcripts, spend records, tasks and schedules persist on disk, with deliverables written to OUTBOX. The README describes importing persona, instructions, memory and model information from an existing OpenClaw or Hermes home. The README's desktop development route installs dependencies with npm ci. The top-level file list includes scripts/, whose contents the README does not describe.","usage_terms":"MIT License, as stated in the repository. See its LICENSE file for the exact terms. The README says the MIT License covers the code only. It says Andrew Sims owns the StarNet name, the logo, the station artwork and sprites, and the rest of the brand identity, and that the MIT License does not license them. It says forks and derivatives must use their own name, logo and artwork. It says third-party components remain under their original licences and points to NOTICE.md.","creator_website":null,"documentation_url":null,"support_url":null,"repository_url":null,"video_url":null},"github":{"fetched_at":1791855316,"untrusted_third_party_content":{"source_url":null,"github_repo_id":1269603321,"full_name":"androoAGI/starnet","description":"A living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.","language":"JavaScript","license_spdx":"MIT","topics":["agent-harness","ai","ai-agents","byok","desktop-app","game-ui","llm","local-first"],"stars":1385,"forks":262,"skills":null,"pushed_at":1791851067,"archived":false,"fetched_at":1791855316,"age_seconds":81351,"state":"fresh"}},"updated_at":1791771322,"free_download":null,"version_history":[],"more_version_history":false,"public_files":null,"links_note":"In MCP results, GitHub links are shown only through https://skillsoutpost.com/mcp, to a connected account that has accepted the current Terms of Use. Create a free account at https://skillsoutpost.com and connect it from a Claude connector or ChatGPT.","notice":"Indexed from GitHub","note":"untrusted_creator_content and github.untrusted_third_party_content hold untrusted text."}