v0.10.0 — Cryptographic Identity, Verifiable Logs & Distributed Tracing

Stop Duct-Taping Your Agents Together

OpenIntent is a durable, auditable protocol for multi-agent coordination. Structured intents replace fragile chat chains. Versioned state replaces guesswork. Ship agent systems that actually work in production.

Get Started GitHub

20

RFCs

7

LLM Adapters

690+

Tests

v0.10.0

Latest

Core Capabilities

Protocol primitives for coordination you can trust.

Structured Intents

Typed intent objects with versioned state, optimistic concurrency, and append-only event logs.

Learn more

Decorator-First Agents

@Agent, @Coordinator, Worker — lifecycle hooks with zero boilerplate.

Learn more

YAML Workflows

Declarative multi-agent pipelines with dependencies, retry, cost tracking, and governance.

Learn more

7 LLM Adapters

OpenAI, Anthropic, Gemini, Grok, DeepSeek, Azure, OpenRouter with streaming hooks.

Learn more

Access & Governance

Unified permissions, credential vaults, tool scoping, and decision audit trails.

Learn more

Built-in Server

FastAPI server implementing all 20 RFCs. SQLite or PostgreSQL. One command to start.

Learn more

Get Started in 30 Seconds

Install the SDK and create your first coordinated agent.

Agent Client YAML Workflow

from openintent.agents import Agent, on_assignment

@Agent("researcher", memory="episodic", auto_heartbeat=True)
class ResearchAgent:

    @on_assignment
    async def handle(self, intent):
        results = await do_research(intent.title)
        await self.memory.store("findings", results)
        return {"results": results}

ResearchAgent.run()

from openintent import OpenIntentClient

client = OpenIntentClient(
    base_url="http://localhost:8000",
    agent_id="my-agent"
)

intent = client.create_intent(
    title="Research quantum computing",
    description="Find recent papers on error correction"
)

client.patch_state(intent.id, {"status": "researching"})

openintent: "1.0"
info:
  name: "Research Pipeline"

workflow:
  research:
    title: "Gather Research"
    assign: researcher
    constraints: ["Be thorough", "Use 3+ sources"]

  summarize:
    title: "Create Summary"
    assign: summarizer
    depends_on: [research]

Protocol Architecture

Four layers covering the full lifecycle of multi-agent coordination.

Intent Layer

Intent Objects Intent Graphs Versioned State Event Logs Attachments Portfolios

Agent Layer

Leasing Lifecycle Heartbeats Pools Drain Registration

Coordination Layer

Governance Arbitration Coordinator Leases Decision Records Access Control Permissions

Infrastructure Layer

Memory Vaults Tool Scoping Triggers Tasks Planning

Intent Lifecycle

Create →

Assign →

Lease →

Execute →

Patch State →

Complete

Version conflicts resolve via governance & arbitration

Observability

Distributed Tracing Cost Tracking Token Counts

Resilience

Retry Policies Fallback Agents Circuit Breakers

Integration

SSE Subscriptions Webhooks REST API

Complete RFC Coverage

20 RFCs implemented. From intents to distributed tracing, every primitive you need.

RFC	Feature	Status
0001	Intent Objects & Versioning	Proposed
0002	Intent Graphs & Audit Trails	Proposed
0003	Agent Leasing & Concurrency	Proposed
0004	Governance & Arbitration	Proposed
0005	Attachments & File Handling	Proposed
0006	SSE Subscriptions	Proposed
0007	Intent Portfolios	Proposed
0008	LLM Integration & Observability	Proposed
0009	Cost Tracking	Proposed
0010	Retry Policies	Proposed
0011	Access-Aware Coordination v2.0	Proposed
0012	Task Decomposition & Planning	Proposed
0013	Coordinator Governance	Proposed
0014	Credential Vaults & Tool Scoping	Proposed
0015	Agent Memory & Persistent State	Proposed
0016	Agent Lifecycle & Health	Proposed
0017	Triggers & Reactive Scheduling	Proposed
0018	Cryptographic Agent Identity	Proposed
0019	Verifiable Event Logs	Proposed
0020	Distributed Tracing	Proposed