Odysseus

Open source toolAI workspace

A self-hosted AI workspace for chat, agents, research, documents, email, notes, calendar, and local model workflows.

Homepage Docs Repository

Scanned 15 Oct 2026 · Schema v5 · features v21

Licence: AGPL-3.0-or-later
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Container
shares the host kernel
Regions: —
Not disclosed on the public surface.
Capabilities: 10 / 61
6 partial · 20 fail · 0 not assessed
Agent readiness: 4.5/10 · 4.5/9
read · drive, pre-login surface

Advertised for

Chat and agent tasks using local/API models, shell/files/tools/MCP/skills/memory · Hardware aware model recommendations, downloads and serving · Multi step web research and generated reports · Blind model comparison; AI document editing · IMAP/SMTP email triage; notes, reminders, scheduled agent tasks and CalDAV calendar

Built for

Technical, then semi-technical builders

· README: clone repository, copy .env, Docker Compose; native Python installs also documented.
· Setup covers GPU overlays, private proxies, model endpoints, IMAP/SMTP and CalDAV.

01 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

A dark, monospace landing uses cyan text, coral highlights, a sail mark and flowing background artwork. Its linked setup guide uses GitHub's light repository-and-Markdown layout rather than the landing's visual theme. No commercial pricing page applies to this free self-hosted tool.

Retro-computing

Landing page: captured
Pricing: not applicable
Docs: captured

02 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

Persistent data/ state and bind-mounted logs/model caches; Docker ChromaDB vectors reside in a separate chromadb-data volume.

Snapshots / forks

No compute-instance snapshot/fork. Official odysseus-backup snapshots/restores app data as tar.gz using SQLite backup API; Docker ChromaDB requires separate backup.

Resources & limits

Storage

SQLite default (DATABASE_URL configurable), ChromaDB vectors, local data/uploads/docs/model caches. Docker vectors in separate volume.

Limits & quotas

Operator hardware; configurable validated positive upload limits: chat/memory/ICS 10MB, gallery 100MB, document/email/STT 25MB. No hosted quota system.

GPU

Uses operator GPUs for local-model serving; NVIDIA/AMD overlays, native macOS Metal. Does not provision GPU instances.

Access

Deploy interface

dockerfilecontainer-image

SDK languages

None

Network & secrets

Egress controls

No agent network egress filtering. Post-untrusted-context side-effect approval gate is enabled by default.

Secrets

Admin Vault, integration tokens and provider keys; backup contains Fernet data/.app_key and stored tokens. Not an outside-workload credential-injection proxy.

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

Chat and agent tasks using local/API models, shell/files/tools/MCP/skills/memoryHardware aware model recommendations, downloads and servingMulti step web research and generated reportsBlind model comparison; AI document editingIMAP/SMTP email triage; notes, reminders, scheduled agent tasks and CalDAV calendar

03 Capabilities 10 pass · 6 partial · 20 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 0/2

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Not applicable

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not applicable

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not applicable

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not applicable

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Not applicable

GPU computeGPU-backed instances available.

Not applicable

Multi-regionCompute placeable in more than one geographic region.

Not applicable

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Not applicable

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not applicable

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Partially supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 1/5

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Not supported

Custom domainsBring-your-own domain via CNAME/DNS.

Not supported

Public preview URLsShareable per-deploy / per-branch URLs.

Not applicable

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not applicable

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Not supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not applicable

Email send / receiveSend and/or receive email from the workload.

Supported

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 2/8

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Not supported

SSH accessDirect SSH into workloads.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Not applicable

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Not supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 4/11

Built-in coding agentShips a first-party AI coding agent in the product.

Supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Partially supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Partially supported

BYOK for LLMsBring-your-own LLM provider keys.

Supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not applicable

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not supported

Data 0/1

First-party databasePlatform-provided managed database.

Not applicable

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Partially supported

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 1/2

Scheduled tasksCron / scheduled job primitive.

Supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not applicable

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Not applicable

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not applicable

Organisation & security 2/7

Built-in authPlatform-provided authentication / IAM for workloads.

Supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Partially supported

TeamsMulti-user team accounts.

Partially supported

SharingShare a running workload/resource via link (optionally gated).

Not supported

BYOCRuns inside the customer's own cloud account.

Not applicable

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not applicable

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Cookbooklocal-model-serving
“Hardware-aware model recommendations, downloads, and serving.” raw.githubusercontent.com
Deep Researchdeep-research
“Multi-step web research with source reading and report generation.” raw.githubusercontent.com
AI email triageai-email-triage
“IMAP/SMTP inbox with triage, tags, summaries, reminders, and reply drafts.” raw.githubusercontent.com
CalDAV calendarcaldav-calendar
“Notes, Tasks + Calendar — reminders, todos, scheduled agent tasks, and CalDAV sync.” raw.githubusercontent.com

04 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

4.5/10

3 full · 3 partial · 45% of applicable checks

llms.txt
Not supported
“https://odysseus-dev.github.io/odysseus/llms.txt returned 404.”
llms-full.txt
Not supported
“https://odysseus-dev.github.io/odysseus/llms-full.txt returned 404.”
robots.txt AI policy
Partially supported
“https://odysseus-dev.github.io/odysseus/robots.txt returned 404: default-allow.”
JSON-LD
Not supported
“Fresh landing HTML contains no application/ld+json script.”
Sitemap
Not supported
“https://odysseus-dev.github.io/odysseus/sitemap.xml returned 404; robots absent, no alternate pointer.”
Meta tags
Partially supported
“Descriptive title and description, no OpenGraph tags in fetched landing.”
Markdown negotiation
Partially supported
“Accept:text/markdown returns text/html; .md landing variant 404. Raw GitHub README/setup/skills are substantive Markdown.”
Content efficiency
Supported
“4332 readable text chars / 56964 HTML bytes (~7.6%), excluding script/style: >5%.”
Docs discoverable
Supported
“Landing Get started links repository README; README links Setup Guide first-class.”
Machine-readable pricing
Not applicable
“Self-host-only AGPL app; no hosted pricing.”
No anti-bot wall
Supported
“Public landing, raw documentation, gh metadata and well-known probes fetched without challenge.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

4.5/9

3 full · 3 partial · 50% of applicable checks

Public API
Supported
“Official Claude/Codex skills document scoped HTTP endpoint methods and payloads for memory/calendar/documents/email/Cookbook.”
OpenAPI spec
Not supported
“No published specification in repository tree/setup; public openapi.json 404.”
MCP server
Not supported
“MCP is consumed internally; no documented first-party external MCP server.”
SDK packages
Not supported
“Python integration helper scripts, no official packaged client SDK.”
Auth documented
Supported
“Integration README documents Bearer ODYSSEUS_API_TOKEN and server-enforced per-tool scopes/403 behavior.”
Self-serve credentials
Not applicable
“Self-host-only; no hosted signup/credential endpoint.”
Webhooks
Partially supported
“Setup documents admin-gated webhook management but not signing/payload reference.”
CLI tool
Supported
“Official scripts/odysseus-backup with documented commands and JSON output; integration API command helper also documented.”
Error model
Partially supported
“Integration skills document intentional 403 permission restrictions, but no comprehensive JSON error schema.”
Rate limits documented
Not applicable
“No hosted API rate-limit surface.”
Agent config files
Partially supported
“Official Claude and Codex SKILL.md bundles; no root AGENTS.md or public well-known agent discovery.”

05 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 2

Claude Code Anthropic
Supported
“This directory contains the Claude Code skill bundle for Odysseus.”
Source raw.githubusercontent.com
Codex CLI OpenAI
Supported
“This directory contains the Codex plugin/skill bundle for Odysseus.”
Source raw.githubusercontent.com

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

06 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 0

No attestations found on the public surface. Empty means nothing is advertised, after checking, not that nothing was checked.

Regions —

No region list captured.

07 Open source AGPL-3.0-or-later · fetched by machine, not quoted from marketing

Licence & repository

Licence: AGPL-3.0-or-laterOSI
Primary language: Python
Stars: 93,478
Forks: 1,593
Created: 31 May 2026
Archived: No

Activity

Last commit: 14 Oct 2026
Latest release: —
Issues open / closed: 1123 / 1208 · 52% closed

GraphQL returned no GitHub releases. README documents mutable branch/version image tags and immutable version-SHA build pins; do not equate image versions with GitHub releases.

Fetched via gh on 15 Oct 2026.

Self-hosting

Methods: composedockersource-build
You operate: sqlitechromadbsearxngntfy

Self-host only: free under AGPL-3.0-or-later plus own infrastructure/model-provider costs. Compose maps 127.0.0.1:7011 to container port 7000 (README and compose agree; setup guide still says host 7000). Native Linux/Windows manual runs use 7000; macOS launcher uses 7860. Official multi-arch GHCR images and immutable version-SHA pins are documented; setup warns package visibility may force local-build fallback. Native Python 3.11+; GPU passthrough is opt-in, macOS Metal requires native deployment. Agent shell/files are unsandboxed; tool approval after untrusted context is enabled by default. Host Docker socket access is explicit opt-in. Docker ChromaDB uses a separate volume not included by the data-directory backup helper.

Documentation signals 5/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
Not supportedChangelog
Not supportedOpenAPI
Not supportedllms.txt
SupportedExamples
SupportedArchitecture doc

08 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: Unknown

Activity

Last release: — github.com
Last blog post: — odysseus-dev.github.io

Presence 2

Links found on the public surface scanned; not an exhaustive search.

09 Sources & method How this entry was produced

Public surface only

Everything here was read from odysseus-dev.github.io's unauthenticated pages, docs, pricing and repository on 15 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All AI workspace products →