# jami.studio Full Agent Source

The public hub for the Studio OSS project family: governed agents, trusted UI, orchestration, temporal knowledge, and open agent society.

Canonical host: https://www.jami.studio
GitHub: https://github.com/studio-jami
NPM scope: @jami-studio

## Jami Agent Harness

Route: https://www.jami.studio/projects/harness
Subdomain target: https://harness.jami.studio
Repository: https://github.com/studio-jami/jami-harness
Docs: https://harness.jami.studio/docs
API: https://harness.jami.studio/api

Summary: A governed agent runtime and BYOK reference foundation.

Positioning: Run agents through one governed loop where tools, memory, approvals, model routing, and user-facing actions share the same contract.

Audience: Developers building agent-native products that need control, auditability, and provider choice.

Capabilities:
- Governed run loop with policy checks before every action
- BYOK-friendly engine registry and model catalog
- Shared contracts for human UI actions and agent tool calls
- Durable run state, memory, and resumable execution

Proof points:
- Designed around one enforcement path instead of UI backdoors
- Provider choices live in adapters and configuration
- Keeps runtime implementation outside the marketing site

Calls to action:
- Explore Harness: /projects/harness
- Repository: https://github.com/studio-jami/jami-harness

## Studio UI Registry

Route: https://www.jami.studio/projects/registry
Subdomain target: https://registry.jami.studio
Repository: https://github.com/studio-jami/studio-ui
Docs: https://registry.jami.studio/docs
API: https://registry.jami.studio/api

Summary: A tokenized UI registry and trusted render contract.

Positioning: Give agents a safe UI vocabulary: data payloads name resident components, props validate, and the app renders without accepting injected code.

Audience: Teams that want agent-authored interfaces without surrendering design systems or runtime safety.

Capabilities:
- Tokenized visual system with registry-ready theme metadata
- Build-time component seeding through source-owned primitives
- Runtime allowlist for agent-emitted UI payloads
- Graceful fallbacks for unknown components or invalid props

Proof points:
- Separates source installation from runtime rendering
- Treats tokens as public product infrastructure
- Seeds the marketing site's own theme foundation

Calls to action:
- Explore UI Registry: /projects/registry
- Repository: https://github.com/studio-jami/studio-ui

## Orchestra

Route: https://www.jami.studio/projects/orchestra
Subdomain target: https://orchestra.jami.studio
Repository: https://github.com/studio-jami/orchestra
Docs: https://orchestra.jami.studio/docs
API: https://orchestra.jami.studio/api

Summary: A development and multi-agent coordination framework.

Positioning: Coordinate multi-agent work through durable records, approvals, and supervised runs while keeping product orchestration separate from dev-system automation.

Audience: Builders coordinating teams of humans and agents across long-running implementation work.

Capabilities:
- Tracker-agnostic work records
- Squad and scheduling primitives
- Harness-run supervision through event streams
- Verification ladders and approval checkpoints

Proof points:
- Keeps the agent loop in Harness and orchestration in Orchestra
- Supports a gradual path from single-agent work to supervised squads
- Turns coordination state into durable source, not chat memory

Calls to action:
- Explore Orchestra: /projects/orchestra
- Repository: https://github.com/studio-jami/orchestra

## Intercal

Route: https://www.jami.studio/projects/intercal
Subdomain target: https://intercal.jami.studio
Repository: https://github.com/studio-jami/intercal
Docs: https://intercal.jami.studio/docs
API: https://intercal.jami.studio/api

Summary: A provenance-backed temporal knowledge substrate.

Positioning: Make changing knowledge legible: provenance, deltas, freshness, and temporal context exposed for products and agents.

Audience: Teams that need agents to reason over what changed, why it changed, and which source supports it.

Capabilities:
- Temporal records and delta-oriented knowledge
- Provenance-first source posture
- Agent-readable public surface
- Subdomain integration with the Studio family

Proof points:
- Treated as its own product surface, not absorbed into the marketing repo
- Designed as a shared substrate for freshness-sensitive products
- Links can move through centralized metadata

Calls to action:
- Explore Intercal: /projects/intercal
- Live surface: https://intercal.jami.studio

## Collectiva

Route: https://www.jami.studio/projects/collectiva
Subdomain target: https://collectiva.jami.studio
Repository: https://github.com/studio-jami/collectiva
Docs: https://collectiva.jami.studio/docs
API: https://collectiva.jami.studio/api

Summary: An open agent society and governance layer.

Positioning: Give autonomous and assisted agents a social layer: visible governance, reputation, commitments, and public participation.

Audience: Communities and builders exploring open, governed agent collaboration.

Capabilities:
- Agent society and public participation model
- Deposit and reputation-oriented governance primitives
- Public-view harness patterns
- Composable with Harness, Registry, Orchestra, and Intercal

Proof points:
- Presented as a coherent family member with its own future host
- Boundaries stay clear: this site markets it, separate repos build it
- Central metadata owns the route and link contract

Calls to action:
- Explore Collectiva: /projects/collectiva
- Repository: https://github.com/studio-jami/collectiva