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-0.2.2.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-0.2.2-py3-none-any.whl (171.9 kB view details)

Uploaded Python 3

File details

Details for the file sibyl_core-0.2.2.tar.gz.

File metadata

  • Download URL: sibyl_core-0.2.2.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-0.2.2.tar.gz
Algorithm Hash digest
SHA256 d4c4c9737e3ea72830f14b1a334f3cb0261218a683f496b6f0939f33bcb7533b
MD5 b9df35d16ccf692bc9ea8c280636accb
BLAKE2b-256 a486a8e51a41f8664a641d3dfea5185e095b3848fa99299585d1f1ce4fdf1b1a

See more details on using hashes here.

Provenance

The following attestation bundles were made for sibyl_core-0.2.2.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-0.2.2-py3-none-any.whl.

File metadata

  • Download URL: sibyl_core-0.2.2-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-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 f41f7834d2049c08630a17d2d3633201a6d4135ea63882724fd7f476c1b819c0
MD5 3fb4eeff95cfdfb78928685914049cd9
BLAKE2b-256 b48af69f3b0d777e1042bf757e1205f4f93f7f836d7b79e2fda83fa4d0cafd90

See more details on using hashes here.

Provenance

The following attestation bundles were made for sibyl_core-0.2.2-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