Skip to main content

Core library for Sibyl - domain models, graph operations, and knowledge retrieval

Project description

sibyl-core

Core library for Sibyl — domain models, graph operations, retrieval algorithms, and tool implementations. Shared foundation for the API server and CLI.

Quick Reference

# Install
uv add sibyl-core

# Development
moon run core:lint        # Ruff check
moon run core:typecheck   # Pyright
moon run core:test        # Pytest

What's Here

  • models/ — Domain entities (Task, Project, Epic, Agent, Source, etc.)
  • graph/ — FalkorDB/Graphiti client, entity management
  • retrieval/ — Hybrid search (semantic + BM25), fusion, deduplication
  • tools/ — MCP tool implementations (search, explore, add, manage)
  • tasks/ — Workflow engine, dependency resolution
  • auth/ — JWT primitives, password hashing

Structure

src/sibyl_core/
├── models/
│   ├── entities.py       # Entity, EntityType, base classes
│   ├── tasks.py          # Task, Project, Epic, Milestone
│   ├── agents.py         # AgentRecord, WorktreeRecord, ApprovalRecord, Checkpoint
│   ├── sources.py        # Source, Document
│   └── responses.py      # API response models
├── graph/
│   ├── client.py         # GraphClient (connection, write lock)
│   ├── entities.py       # EntityManager (CRUD, search)
│   └── relationships.py  # RelationshipManager
├── retrieval/
│   ├── hybrid.py         # Hybrid search orchestration
│   └── fusion.py         # Score fusion (RRF)
├── tools/
│   ├── search.py         # Semantic search
│   ├── explore.py        # Graph navigation
│   ├── add.py            # Entity creation
│   └── manage.py         # Task workflow, admin
└── tasks/
    ├── workflow.py       # State machine, transitions
    └── manager.py        # Task operations

Usage

Models

from sibyl_core.models import (
    Entity, EntityType, Task, TaskStatus, Project, Epic,
    AgentRecord, AgentStatus, WorktreeRecord, ApprovalRecord,
)

task = Task(
    name="Implement OAuth",
    content="Add Google and GitHub OAuth",
    project_id="proj_abc",
    status=TaskStatus.TODO,
)

Agent Models

from sibyl_core.models import (
    AgentRecord, AgentStatus, AgentType,
    WorktreeRecord, WorktreeStatus,
    ApprovalRecord, ApprovalType, ApprovalStatus,
    AgentCheckpoint,
)

# Agent record (persistent state)
agent = AgentRecord(
    name="OAuth Implementation Agent",
    status=AgentStatus.WORKING,
    agent_type=AgentType.IMPLEMENTER,
    task_id="task_abc",
    tokens_used=15000,
    cost_usd=0.45,
)

# Git worktree for isolation
worktree = WorktreeRecord(
    agent_id="agent_xyz",
    path="/worktrees/agent-xyz",
    branch="agent/oauth-impl",
    status=WorktreeStatus.ACTIVE,
)

# Human-in-the-loop approval
approval = ApprovalRecord(
    agent_id="agent_xyz",
    approval_type=ApprovalType.FILE_WRITE,
    summary="Write to config.py",
    status=ApprovalStatus.PENDING,
)

# Session checkpoint for resume
checkpoint = AgentCheckpoint(
    agent_id="agent_xyz",
    session_id="sess_123",
    conversation_summary="Implementing OAuth...",
    current_step="Writing auth module",
)

Graph Client

from sibyl_core.graph import GraphClient, EntityManager

client = await GraphClient.create()
manager = EntityManager(client, group_id=str(org_id))

# CRUD
await manager.create(entity)
entity = await manager.get_by_id("entity_abc")
results = await manager.search("authentication patterns", limit=20)

Write Concurrency

All writes use the write lock to prevent FalkorDB corruption:

async with client.write_lock:
    await client.execute_write_org(org_id, query, **params)

# Or use EntityManager (handles locking internally)
await manager.create(entity)

Task Workflow

from sibyl_core.tasks import TaskManager

manager = TaskManager(entity_manager)
await manager.start_task(task_id)
await manager.complete_task(task_id, learnings="Key insight...")
await manager.block_task(task_id, reason="Waiting on API")

Entity Types

Type Description
pattern Reusable coding patterns
episode Temporal learnings
task Work items with workflow
project Container for tasks
epic Feature-level grouping
source Documentation sources
document Crawled content
agent AI agent records
worktree Git worktree isolation
approval Human approval requests
checkpoint Agent session state

Relationship Types

from sibyl_core.models import RelationshipType

# Knowledge
RelationshipType.APPLIES_TO, REQUIRES, CONFLICTS_WITH, SUPERSEDES

# Task
RelationshipType.BELONGS_TO, DEPENDS_ON, BLOCKS, REFERENCES

# Agent
RelationshipType.WORKS_ON, USES_WORKTREE, CHECKPOINTED_AS, REQUESTED_BY

Configuration

SIBYL_OPENAI_API_KEY=sk-...         # Required (embeddings)
SIBYL_FALKORDB_HOST=localhost
SIBYL_FALKORDB_PORT=6380
SIBYL_ANTHROPIC_API_KEY=...         # Optional (agents)

Key Patterns

Multi-tenancy: Every operation requires org context

manager = EntityManager(client, group_id=str(org.id))

Node labels: Graphiti creates Episodic and Entity nodes

WHERE (n:Episodic OR n:Entity) AND n.entity_type = $type

Creation paths: LLM-powered (create) vs direct (create_direct)

await manager.create(entity)         # Slower, richer extraction
await manager.create_direct(entity)  # Faster, no LLM

Testing

# With mock LLM (fast, deterministic)
SIBYL_MOCK_LLM=true uv run pytest tests/

# Live model tests (costs money)
uv run pytest tests/live --live-models

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sibyl_core-0.2.1.tar.gz (222.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sibyl_core-0.2.1-py3-none-any.whl (171.9 kB view details)

Uploaded Python 3

File details

Details for the file sibyl_core-0.2.1.tar.gz.

File metadata

  • Download URL: sibyl_core-0.2.1.tar.gz
  • Upload date:
  • Size: 222.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sibyl_core-0.2.1.tar.gz
Algorithm Hash digest
SHA256 2364bda55836865282dced5683dfb53a584658da24a112a9a838f33c5136fefd
MD5 f6874d077d3a71ebdde008582358b526
BLAKE2b-256 ebf9de49c78f6bb73e039a9a51b630b495ba3d621a3a29ae9880b03c94021357

See more details on using hashes here.

Provenance

The following attestation bundles were made for sibyl_core-0.2.1.tar.gz:

Publisher: publish.yml on hyperb1iss/sibyl

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sibyl_core-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: sibyl_core-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 171.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sibyl_core-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 2f6b4bb94670558dcd96e5ac9ebf73178fe6a819d96cda06a1ebf44e7e5baa35
MD5 1c05525a0682b170d97dd23baa22d350
BLAKE2b-256 a9d54a5b2a79fd269ddc2627713de339d08b8ac3571b89d0fb7dd3e6d86da4f4

See more details on using hashes here.

Provenance

The following attestation bundles were made for sibyl_core-0.2.1-py3-none-any.whl:

Publisher: publish.yml on hyperb1iss/sibyl

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page