{"product":{"id":"platform","name":"Adeno Platform","tagline":"Architecture overview of the whole platform","group":"Platform"},"generated_at":"2026-08-22T22:13:20Z","base_url":"https://docs.adeno.ltd","pages":[{"slug":"platform","title":"Adeno Platform Overview","description":"Adeno is a modular platform for autonomous AI workflows. Services share a common trust fabric (CAuth), a package ecosystem (APS + Uracil), an encrypted data hub (Corpus), and an inference gateway (Athena), so each product stays small and composable instead of becoming a monolith.","url":"https://docs.adeno.ltd/docs/platform","markdown_url":"https://docs.adeno.ltd/docs/platform.md","headings":[{"level":2,"text":"Core principles","anchor":"core-principles"},{"level":2,"text":"The platform in layers","anchor":"the-platform-in-layers"},{"level":2,"text":"Cross-service integration","anchor":"cross-service-integration"},{"level":2,"text":"CAuth transtokens","anchor":"cauth-transtokens"},{"level":2,"text":"Package and runtime model","anchor":"package-and-runtime-model"},{"level":2,"text":"Where to go next","anchor":"where-to-go-next"}],"word_count":412,"markdown":"# Adeno Platform Overview\n\nAdeno is a modular platform for autonomous AI workflows. Services share a common trust fabric (CAuth), a package ecosystem (APS + Uracil), an encrypted data hub (Corpus), and an inference gateway (Athena), so each product stays small and composable instead of becoming a monolith.\n\n## Core principles\n\n- **Service isolation** — every capability is a separate service with explicit contracts.\n- **Shared trust** — one authentication and billing fabric across products.\n- **Consent-gated data** — user data moves only with explicit consent scopes and TTLs.\n- **Rootless least-privilege execution** — extensions run sandboxed with declared capabilities.\n- **Automation-first** — errors route to automated remediation before humans.\n\n## The platform in layers\n\n| Layer | Components | Role |\n|---|---|---|\n| Trust & identity | CAuth | Authentication, accounts, usage accounting, billing |\n| Inference | Athena | LLM routing, model registry, GGUF/Neuron sidecars |\n| Data | Corpus | Encrypted consent-gated cross-service data hub |\n| Packages | APS + Uracil | `.aps` solution packages, `.ura` rootless bundles |\n| Orchestration | Arachne | Graph workflows, OAuth connectors, campaign orchestration |\n| Products | Keryx, Kairos, Mnemosyne | Outreach automation, productivity suite, sensor-fusion research |\n| Reliability | Eunomia | Error reporting, triage, AI patch → sandbox → gated promotion |\n| Clients | Hermes | Client-side hosting + OTA hot-patches in a WASM enclave |\n\n## Cross-service integration\n\nServices are intentionally interoperable:\n\n- Keryx uses **CAuth** to authenticate users and **Athena** to run inference.\n- Keryx pushes memory and campaign context into **Corpus** for consented reuse.\n- **Arachne** orchestrates email and campaign actions across Keryx and Kairos.\n- **Eunomia** receives a bug report, asks Athena to generate a patch, sandboxes it in Uracil, then promotes it through CI/security/compliance gates.\n- APS packages are distributed by the registry and consumed by Uracil at runtime.\n\n## CAuth transtokens\n\nAll major services use CAuth transtokens for request authentication:\n\n- Transtokens are JWTs signed with `CAUTH_SECRET_KEY` (HS256).\n- Claims include `sub`, `iat`, `exp`, `type`, and `jti`.\n- `transtoken` lifetime ≈ 15 minutes; `anontoken` ≈ 2 days.\n- Attach as `Authorization: Bearer <transtoken>`.\n- Services validate tokens with the shared secret.\n\n## Package and runtime model\n\nThe Adeno Package Service (APS) distributes two package styles:\n\n- **Python packages** with `entry_point` and optional dependencies\n- **Uracil service bundles** with `runtime`, `service`, and `permissions` sections\n\nUracil executes installed bundles with explicit permissions: each bundle carries a `manifest.json` describing identity, runtime ABI, permissions, and functions. Functions execute as subprocesses (Python or native C++). Campaigns provide persistent runtime contexts with cleanup semantics.\n\n## Where to go next\n\n- Browse the [product catalog](/api/products)\n- Read the [AI-friendly index](/llms.txt) or the full dump at [/llms-full.txt](/llms-full.txt)\n"}]}