Project - AI management, online and open source.

est. 2026 - lfg

01 / what

A project management system where AI agents are first-class, not an integration.

context

Engineering teams ship alongside Claude Code, Cursor, Devin, and their own in-house agents. The work those agents do - the PRs they draft, the tasks they pick up, the reviews they run - doesn't fit cleanly into tools designed for humans passing tickets to humans.

Paimos treats agents as peers. Same board, same status, same audit trail as every other contributor. Built for teams doing agentic development, equally at home for the solo engineer running a kanban on their weekend project.

Code-aware agents get more than tickets: linked repos, structured project manifests, issue → file anchors, and a mixed-context retrieval API /projects/:id/retrieve. The agent doesn't have to grep six issues to know which repo to clone or where the work actually lives.

02 / who

Two audiences, one tool - without the split personality.

for

§professional

Engineering teams doing agentic software development. Managing Claude Code runs, Cursor agents, internal frameworks - alongside humans - as part of one workflow.

Jira wasn't designed for this. Linear is closer but still treats AI as a sidecar. Paimos was built for it from the name on.

§personal

Solo engineers with side projects. Same tool. No enterprise bloat, no process tax, no seat licenses.

A kanban for your weekend repo should feel as clean as one for a team of twenty - and not require you to pretend you're a "product owner".

03 / specs

Designed for you, the EU, and only god knows who!

NIS2-aligned

audit trails, incident workflows, access control, and operator-grade runbooks

GDPR-conscious

data minimization, export/delete workflows, retention controls, EU-hostable

Self-hostable

single docker compose; run on your own tin; no SaaS dependency

AGPL-3.0

source always available; copyleft - modifications must be shared

Made in Graz

designed and built in Graz, Austria; EU-hosted by default

Enterprise-capable

SSO, RBAC, auditability, hardened deployment path - serious-org ready

Single sign-on

OIDC-ready login, strong session controls, and serious-org identity integration

Audit trails

operator-visible change history, incident evidence, retention controls, and reviewable events

Local AI roadmap

designed to run alongside local inference - Ollama, LM Studio, vLLM, llama.cpp on the roadmap, not in today's build

Zero telemetry

no analytics, no tracking pixels, no forced phone-home - your users stay yours

Air-gap friendly

no mandatory cloud dependency; supports no-egress deployments

Scriptable API

REST + OpenAPI contract; automation-first from day one

Code-aware agents

structured project facts agents can read - linked repos, manifests, issue-to-file anchors, mixed-context retrieval

Built-in AI assist

in-app prose optimize, translate, spec-out, suggest-enhancement, sub-task generation - eleven admin-tunable actions, audit-clean

SBOM + signed releases

CycloneDX manifests, checksums, signed artifacts, verifiable provenance

Fully inspectable

open codebase, auditable behavior, no black-box trust model

Restore-tested

backup, restore, upgrade, and disaster-recovery paths verified before they matter

04 / status

phase 2 platform phase 1 foss

Open source, agent-native, built in public. Now in Phase 2 (Platform) as of v2.0.0; AGPL-3.0 from day zero.

Paimos is under active development at github.com/markus-barta/paimos. v2.0 earned the Platform reading the brand had reserved for this moment: a structured agent-context layer, an 11-action AI dispatcher, OpenAPI + MCP for integration. Phase 1 (FOSS) stays active alongside; transitions here are additive. Follow the repo; star it if you like what you see.