{"id":34552435,"url":"https://github.com/arkavo-org/arkavo-edge","last_synced_at":"2026-06-13T23:01:41.307Z","repository":{"id":293892666,"uuid":"985428753","full_name":"arkavo-org/arkavo-edge","owner":"arkavo-org","description":"Secure, Sovereign, Self-Healing AI. A Rust-based agent runtime featuring OpenTDF protection and built-in observability.","archived":false,"fork":false,"pushed_at":"2026-05-01T02:55:37.000Z","size":10138,"stargazers_count":11,"open_issues_count":157,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-01T03:18:13.910Z","etag":null,"topics":["agent","agentic-ai","ai","cli","cross-platform","encryption","linux","macos","open-source","opentdf","rust","windows"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/arkavo-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-05-17T18:37:40.000Z","updated_at":"2026-04-29T23:02:37.000Z","dependencies_parsed_at":"2026-03-15T07:06:46.391Z","dependency_job_id":null,"html_url":"https://github.com/arkavo-org/arkavo-edge","commit_stats":null,"previous_names":["arkavo-org/arkavo-edge"],"tags_count":223,"template":false,"template_full_name":null,"purl":"pkg:github/arkavo-org/arkavo-edge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arkavo-org%2Farkavo-edge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arkavo-org%2Farkavo-edge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arkavo-org%2Farkavo-edge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arkavo-org%2Farkavo-edge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arkavo-org","download_url":"https://codeload.github.com/arkavo-org/arkavo-edge/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arkavo-org%2Farkavo-edge/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32522252,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-02T01:12:54.858Z","status":"online","status_checked_at":"2026-05-02T02:00:05.923Z","response_time":132,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","cli","cross-platform","encryption","linux","macos","open-source","opentdf","rust","windows"],"created_at":"2025-12-24T08:01:31.104Z","updated_at":"2026-06-13T23:01:41.293Z","avatar_url":"https://github.com/arkavo-org.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Arkavo Edge\n\nInstant, secure orchestration for AI agents—launch, mesh, and monitor in real time.\n\n## Quick Start\n\n### Install on macOS\n\nDownload the installer from the [releases page](https://github.com/arkavo-org/arkavo-edge/releases), open the .pkg file, and follow the installation wizard.\n\n**For advanced users:** Install via Homebrew\n```bash\nbrew tap arkavo-org/homebrew-arkavo\nbrew trust --formula arkavo-org/arkavo/arkavo  # required on Homebrew 5.2+\nbrew install arkavo\n```\n\n### Install on Linux\n```bash\nbrew tap arkavo-org/homebrew-arkavo\nbrew trust --formula arkavo-org/arkavo/arkavo  # required on Homebrew 5.2+\nbrew install arkavo\n```\n\n**Raspberry Pi 5:** Download ARM64 binary from [releases](https://github.com/arkavo-org/arkavo-edge/releases). See [deployment guide](docs/raspberry-pi-deployment.md) for setup. First run auto-selects an edge model for the device (Pi 5 → Gemma 4 E4B).\n\n### Install on Windows\nDownload the installer from the [releases page](https://github.com/arkavo-org/arkavo-edge/releases) and run the .exe file.\n\n### Launch\n```bash\n# Start an agent (zero config)\narkavo\n\n# Or launch web UI\narkavo ui\n```\n\nThat's it. No configuration files, no setup. Agents auto-discover via mDNS and form a mesh.\n\nOn first run, Arkavo downloads two local models sized to your device — a small model for fast routing (Gemma 4 E2B) and a larger model for inference (Gemma 4 12B on desktop/workstation; Gemma 4 E4B on a Raspberry Pi 5).\n\n### Trusting an agent\n\nTo authorize an agent (e.g. from another device), show its identity QR — the agent's `DID:key` and entitlements:\n\n```bash\narkavo agent run --trust   # or simply: arkavo --trust\n```\n\n## Coming from OpenClaw?\n\nSee the [migration guide](docs/openclaw-migration-guide.md) for a full comparison: what you gain (budget controls, TDF encryption, PII preflight, offline operation), what's different, and step-by-step setup.\n\n## Why Arkavo?\n- **Zero config:** Just run `arkavo`. Auto-naming, auto-routing, auto-discovery.\n- **Fast:** Low-latency agent-to-agent communication (benchmarkable from source — see [Building from Source](#building-from-source)).\n- **Visual:** See live agent communication flows in real-time.\n\n## SwarmKit\n\nDeclarative multi-agent kits where each role declares its own TDF Attribute Release Policy. The orchestrator constructs role-scoped policies before any data reaches the role — push the trust boundary inward.\n\n```bash\n# Launch any kit at gateway boot\nARKAVO_SWARMKIT_PATH=examples/code-review-kit/code-review-kit.swarmkit.yaml arkavo\n```\n\nFour shipped kits: `campaign-kit`, `code-review-kit`, `vrm-production-kit`, `compliance-kit`. Full guide: [docs/SWARMKIT.md](docs/SWARMKIT.md). To validate a kit manifest from source, see [Building from Source](#building-from-source).\n\n## Features\n- **SwarmKit** - Declarative multi-agent kits with per-role TDF attribute-release policies. Four shipped examples covering marketing, code review, creative, and regulated domains. See [docs/SWARMKIT.md](docs/SWARMKIT.md).\n- Multi-provider routing (OpenAI, Anthropic, Gemini, Kimi, DeepSeek, local models)\n- **Local edge models via llama.cpp** - Gemma 4 (E2B/E4B/12B) by default; Ministral 3B/8B (with vision) also supported\n- Cost-aware model selection (real per-token estimates on full macOS/Linux builds; the musl-slim and Windows binaries use an approximate estimator)\n- iOS simulator automation (macOS only)\n- Security scanning (Semgrep, OSV, SBOM)\n\n## Usage Examples\n\n### Chat\n```bash\n# Use any provider with API key\nGEMINI_API_KEY=your-key arkavo chat --prompt \"Hello\"\nDEEPSEEK_API_KEY=your-key arkavo chat --prompt \"Explain Rust\"\n```\n\n### Context Control Demo\nThe Autonomous Refactor demo demonstrates Active Context Management. It simulates a large-scale \"breaking change\" refactor that generates extensive compiler output, showing how the Context Ledger maintains a small active window while preserving data access.\n\n```bash\ncd examples/autonomous_refactor\n./run_demo.sh\n```\n\n### Custom Agent Config (Optional)\n```bash\narkavo agent init my-agent  # Creates AGENTS.md template\n# Edit AGENTS.md to set model, capabilities, API keys\narkavo  # Runs with your config\n```\n\n### Security (Optional)\n\n**OpenTDF Integration:** Fine-grained access control for MCP tools via [OpenTDF](https://opentdf.io). Set `OPENTDF_BASE_URL`, `OIDC_ISSUER`, and `AUD` environment variables.\n\n## Coding Agent Toolset\n\nThe agent uses these MCP tools in-process during `chat` and `task` — there's no separate server to start. Tools that shell out to an external binary register only when that binary is on `PATH` (noted below).\n\n### Code Search \u0026 Intelligence\n- **codegrep_search**: Fast repository-wide code search with ripgrep\n- **struct_find_replace**: Language-aware structural search and replace with Comby\n- **syntax_tree**: AST parsing for syntax-aware code analysis with tree-sitter\n\n### Security \u0026 Quality (require the named binary on `PATH`)\n- **sec_semgrep**: SAST scanning with Semgrep\n- **deps_osv**: Dependency vulnerability scanning with OSV-Scanner\n- **sbom_syft**: SBOM generation with Syft\n\n### Test \u0026 Automation\n- **browser_cdp**: Chrome DevTools Protocol automation via chromiumoxide\n- **test_run**: Multi-language test runner (pytest, jest, go test, cargo test, xcodebuild)\n\n### Ephemeral Workspaces (requires Docker/Podman)\n- **workspace_container**: Container-based isolated execution with resource quotas\n\nThese nine tools are the ones the running agent can call (the binary also registers git, GitHub, web-search, shell, and TDF tools — see the full reference below).\n\n### Benchmark harness\n\nSWE-bench evaluation lives in the separate `arkavo-mcp-bench` crate, run from source — it is **not** a registered agent tool (it depends on the orchestration engine, which would form a dependency cycle if exposed through the tool registry).\n\nSee [docs/coding-agent-toolset.md](docs/coding-agent-toolset.md) for complete tool documentation.\n\n## Platform Support\n\n| Platform | Architecture | Features |\n|----------|-------------|----------|\n| macOS    | ARM64 (Apple Silicon) | Full support including iOS testing, local/remote LLM, mDNS |\n| Linux    | x86_64, ARM64 | Full support with local/remote LLM, mDNS |\n| Linux (musl) | x86_64 | Static/slim binary with memory and mDNS support |\n| Windows  | x86_64 | Memory, remote LLM, and mDNS support (no iOS testing) |\n\nmDNS discovery uses pure Rust implementation (mdns-sd crate) with no system dependencies\n\n**Note:** iOS simulator automation and testing capabilities are only available on macOS.\n\n## Building from Source\n\n### Prerequisites\n\nInstall required build tools:\n\n```bash\n# macOS\nbrew install cmake ccache\n\n# Linux (Debian/Ubuntu)\nsudo apt install cmake ccache build-essential\n\n# Linux (Fedora)\nsudo dnf install cmake ccache gcc-c++\n```\n\n### Setup llama.cpp\n\nClone the llama.cpp dependency (not tracked in git):\n\n```bash\ngit clone https://github.com/ggerganov/llama.cpp vendor/llama.cpp\ncd vendor/llama.cpp\ngit checkout ef570f63087b6a5a2930210a13f87990e8113927\ncd ../..\n```\n\n### Build\n\n```bash\ncargo build\n```\n\nThe default build includes mDNS discovery using a pure Rust implementation (`mdns-sd` crate) that doesn't require system libraries like Avahi or Bonjour. This provides true portability across all platforms.\n\n### Development\n\nThese commands run against the source tree (not the installed binary):\n\n```bash\n# Measure agent-to-agent latency\ncargo bench -p arkavo-protocol --bench a2a_latency\n\n# Validate a SwarmKit manifest\ncargo run -p arkavo-swarmkit --example validate_kit -- \\\n  examples/compliance-kit/compliance-kit.swarmkit.yaml\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farkavo-org%2Farkavo-edge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farkavo-org%2Farkavo-edge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farkavo-org%2Farkavo-edge/lists"}