{"id":48837241,"url":"https://github.com/antigmalabs/ante-preview","last_synced_at":"2026-05-13T09:01:55.076Z","repository":{"id":350988508,"uuid":"1121999804","full_name":"AntigmaLabs/ante-preview","owner":"AntigmaLabs","description":"Ghost in your shell","archived":false,"fork":false,"pushed_at":"2026-04-30T02:30:38.000Z","size":75054,"stargazers_count":16,"open_issues_count":1,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-30T04:22:37.875Z","etag":null,"topics":["agent","agentic-ai","ai-agents","artifical-life","rust","terminal"],"latest_commit_sha":null,"homepage":"https://antigma.ai","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AntigmaLabs.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-23T23:42:44.000Z","updated_at":"2026-04-30T02:30:41.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/AntigmaLabs/ante-preview","commit_stats":null,"previous_names":["antigmalabs/ante-preview"],"tags_count":17,"template":false,"template_full_name":null,"purl":"pkg:github/AntigmaLabs/ante-preview","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AntigmaLabs%2Fante-preview","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AntigmaLabs%2Fante-preview/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AntigmaLabs%2Fante-preview/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AntigmaLabs%2Fante-preview/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AntigmaLabs","download_url":"https://codeload.github.com/AntigmaLabs/ante-preview/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AntigmaLabs%2Fante-preview/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32726686,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","agentic-ai","ai-agents","artifical-life","rust","terminal"],"created_at":"2026-04-15T00:02:34.745Z","updated_at":"2026-05-13T09:01:55.054Z","avatar_url":"https://github.com/AntigmaLabs.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs-site/static/assets/ante.png\" width=\"80\" alt=\"Ante\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://discord.gg/CbAsUR434B\"\u003e\u003cimg src=\"https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord\u0026logoColor=white\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://docs.antigma.ai\"\u003e\u003cimg src=\"https://img.shields.io/badge/Docs-docs.antigma.ai-orange?logo=safari\u0026logoColor=white\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://twitter.com/antigma_labs\"\u003e\u003cimg src=\"https://img.shields.io/badge/X-@antigma__labs-black?logo=x\u0026logoColor=white\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/Antigma\"\u003e\u003cimg src=\"https://img.shields.io/badge/HuggingFace-Antigma-yellow?logo=huggingface\u0026logoColor=white\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n# Ante\n\n\u003e **⚠️ Alpha Preview**\n\u003e Ante is currently in alpha and provided as a research preview. Expect breaking changes and incomplete functionality. macOS and Linux only.\n\nAnte is an AI-native, cloud-native, local-first agent runtime built by [Antigma Labs](https://antigma.ai). A single ~15MB Rust binary with zero runtime dependencies — designed from the ground up for security, performance, and resistance to AI-generated slop.\n\n## Key Features\n\n- **Lightweight agent core** — ~15MB binary, zero dependencies. Built for minimal overhead and maximum throughput.\n- **Native local models** — Built-in local inference integration. No API keys, no internet, no data leaving your device.\n- **Zero vendor lock-in** — Bring your own API key or local model. Switch between 12+ providers freely. No account required.\n- **Client-daemon architecture** — Run as an interactive TUI, headless CLI, or long-lived server (`ante serve`).\n- **Channel integrations** — Run Ante as a Slack or Discord bot with `ante gateway`.\n- **Multi-agent orchestration** — Spawn sub-agents, coordinate complex tasks across independent, decentralized, or centralized architectures.\n- **Extensible** — Custom skills, sub-agents, and persistent memory across sessions.\n- **Benchmark proven** — Topped the Terminal Bench 1.0 and 2.0 leaderboards. Public, reproducible evals.\n\n## Performance\n**We care about the harness not the model nor the prompts.**\n\nAnte is designed for the **cellular-native** thesis: agents lightweight enough to run hundreds of replicas in parallel on a single machine. Its ~15MB Rust core uses a fraction of the memory, CPU, and disk I/O of comparable agents — making mass parallelism practical without specialized infrastructure.\n\nDocker resource usage across 20 parallel tasks (Ante vs Claude Code vs Opencode):\n\n![Resource Usage Comparison](docs-site/docs/benchmarks/compare_animated.gif)\n\nAcross 20 parallel tasks, Ante uses **~7× less peak memory**, **~9× less average CPU**, and generates **~5× less total disk I/O** than Claude Code — while completing the same workload. See the [comparison table](docs-site/docs/benchmarks/compare_table.md) and the [benchmark details](docs-site/docs/benchmarks/eval.mdx) for the evaluation methodology and results.\n\n## Quick Start\n\n### Installation\n\nAnte is distributed as a single, self-contained binary with no external dependencies — just download and run.\n\n```sh\ncurl -fsSL https://ante.run/install.sh | bash\n\n# Install a specific release channel\ncurl -fsSL https://ante.run/install.sh | bash -s -- nightly\n```\n\n### Interactive TUI\n\n```sh\nante\n```\n\n### Headless Mode\n\n```sh\n# Fix a bug\nante -p \"find and fix the failing test in src/auth\"\n\n# Review a diff\ngit diff | ante -p \"review this for security issues\"\n\n# Use a different provider\nante --provider openai --model gpt-5.4 -p \"refactor the database module\"\n\n# Resume a saved session\nante --resume ses_01ARZ3NDEKTSV4RRFFQ69G5FAV -p \"now add tests\"\n\n# Run fully offline with a local GGUF model\nante --offline-model ~/.ante/models/Qwen3.5-9B-Q4_K_M.gguf \\\n  -p \"add error handling to src/main.rs\"\n```\n\n### Server Mode\n\n```sh\nante serve\n```\n\n### Gateway Mode\n\n```sh\nante gateway\n```\n\n### Update Ante\n\n```sh\nante update\n\n# One-off update from a different channel\nante update --channel nightly\n```\n\n## Example Usages with TUI\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n**[Providing Context: Files \u0026 Folders](https://docs.antigma.ai/cookbook/providing-context)**\n\n![Adding file context with @ mentions](docs-site/static/assets/cookbook/files.gif)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n**[Interrupting \u0026 Steering](https://docs.antigma.ai/cookbook/steering)**\n\n![Interrupting the agent with Escape](docs-site/static/assets/cookbook/interrupt.gif)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n**[Models, Providers \u0026 Thinking](https://docs.antigma.ai/cookbook/models-and-thinking)**\n\n![Selecting a model and provider](docs-site/static/assets/cookbook/model.gif)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n**[Subscription Login](https://docs.antigma.ai/cookbook/login)**\n\n![Connecting to a provider via /connect](docs-site/static/assets/cookbook/connect.gif)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n[See all cookbook guides](https://docs.antigma.ai/category/tui-cookbook)\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                         Clients                             │\n│                                                             │\n│   ┌───────────┐    ┌───────────┐    ┌────────────────────┐  │\n│   │    TUI    │    │ Headless  │    │    ante serve      │  │\n│   │  (ante)   │    │ (ante -p) │    │  (stdio / ws)      │  │\n│   └─────┬─────┘    └─────┬─────┘    └─────────┬──────────┘  │\n└─────────┼────────────────┼─────────────────────┼────────────┘\n          │     Op         │                     │\n          ▼                ▼                     ▼\n┌─────────────────────────────────────────────────────────────┐\n│                         Daemon                              │\n│                                                             │\n│   Session ──▶ Turn ──▶ Step                                 │\n│                                                             │\n│   ┌──────────┐  ┌──────────────┐  ┌───────────────────┐     │\n│   │  Tools   │  │  Permission  │  │  Skills / Agents  │     │\n│   └──────────┘  └──────────────┘  └───────────────────┘     │\n└────────────────────────┬────────────────────────────────────┘\n                         │\n                         ▼\n┌─────────────────────────────────────────────────────────────┐\n│                     LLM Providers                           │\n│                                                             │\n│   Anthropic · OpenAI · Gemini · Grok · Open Router · Local  │\n└─────────────────────────────────────────────────────────────┘\n```\n\n## Supported Providers\n\nAnte works with 12+ providers out of the box:\n\n| Provider | Example Models |\n|----------|---------------|\n| Anthropic | Claude Sonnet 4.5, Opus 4.6 |\n| OpenAI | GPT-5 family |\n| Google Gemini | Gemini 3 family |\n| Grok (xAI) | Grok 4 |\n| Open Router | Multiple providers |\n| Local (GGUF) | Any GGUF model via built-in llama.cpp |\n| ...and more | Vertex AI, Zai, Antix, OpenAI-compatible |\n\nConfigure providers via environment variables (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, etc.) or OAuth. Add custom providers in `~/.ante/catalog.json`.\n\n## FAQ\n### Why \u003cspan style=\"color: #f59e0b;\"\u003eAn\u003c/span\u003eother \u003cspan style=\"color: #f59e0b;\"\u003eTe\u003c/span\u003erminal agent\nAnte is fast, lightweight, and the only terminal agent with native local inference support built in.\nWe believe this self-contained agent core that self organize is the centre of the future of agent economy.\n\nIt is just built different. \n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eHow is Ante different than other agents\u003c/b\u003e\u003c/summary\u003e\nOn the high level, it has most of your favorite features (Multi-agents, skills, etc.) of your favorite agents (like Claude Code, Codex, etc.) \n\n- Ante is built from scratch in native Rust, we are obsessed with being self contained, so only essential libraries without framework or runtime dependencies. \n\n- You only need a llm provider configured to run it. Actually if you have the hardware, you don't even need a llm provider because Ante natively support private inference engine. \n\n- This resulted in ~15MB self-contained binary and multi-agent orchestration designed to run hundreds of replicas in parallel at scale.\nSee the [benchmark details](docs-site/docs/benchmarks/eval.mdx) across 20 parallel tasks for concrete numbers.\n\n- No vendor lock-ins, not even ourself. You don't need an account and can reuse your favorite api credentials. \n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eWhy care about runtime optimization like memory and I/O if model inference is usually the biggest bottleneck?\u003c/b\u003e\u003c/summary\u003e\n\nFor one-on-one agent interactions, runtime overhead like memory usage and I/O is often less important than model inference.\n\nBut our vision is much bigger: millions of agents self-organizing and communicating at massive scale. At that point, even small inefficiencies get multiplied millions or billions of times, so runtime optimization becomes economically significant.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eCan I run Ante completely offline?\u003c/b\u003e\u003c/summary\u003e\n\nYes. Ante has a built-in llama.cpp engine that runs GGUF models locally. It handles engine installation, model discovery, and memory management automatically. No API keys or internet connection required.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eCan I use my own custom models or providers?\u003c/b\u003e\u003c/summary\u003e\n\nYes. Create a `~/.ante/catalog.json` file to add or override providers and models with custom endpoints, API keys, and configurations. Any OpenAI-compatible API works.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eWhat is the \u003ccode\u003eante serve\u003c/code\u003e mode for?\u003c/b\u003e\u003c/summary\u003e\n\nServer mode runs Ante as a long-lived daemon that communicates over a structured JSONL protocol. It's ideal for building editor plugins, web UIs, and custom integrations on top of Ante.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eHow do I configure Ante?\u003c/b\u003e\u003c/summary\u003e\n\nSettings live in `~/.ante/settings.json`. You can set your default model, provider, theme, and permission policy. CLI flags override settings for individual sessions. See the [configuration docs](https://docs.antigma.ai/configuration/preference) for details.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eCan I extend Ante with custom skills or sub-agents?\u003c/b\u003e\u003c/summary\u003e\n\nYes. Drop skill files in `~/.ante/skills/` (user-level) or `.ante/skills/` (project-level) using the Open Agent Skills format. Custom sub-agents go in `~/.ante/agents/` with their own prompts, tool sets, and model overrides.\n\u003c/details\u003e\n\n## Documentation\n\nFull documentation is available at [docs.antigma.ai](https://docs.antigma.ai).\nThe source code is in `docs-site/docs`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fantigmalabs%2Fante-preview","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fantigmalabs%2Fante-preview","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fantigmalabs%2Fante-preview/lists"}