AtoCore

Personal context engine that enriches LLM interactions with durable memory, structured context, and project knowledge.

Quick Start

pip install -e .
uvicorn atocore.main:app --port 8100

Usage

# Ingest markdown files
curl -X POST http://localhost:8100/ingest \
  -H "Content-Type: application/json" \
  -d '{"path": "/path/to/notes"}'

# Build enriched context for a prompt
curl -X POST http://localhost:8100/context/build \
  -H "Content-Type: application/json" \
  -d '{"prompt": "What is the project status?", "project": "myproject"}'

# CLI ingestion
python scripts/ingest_folder.py --path /path/to/notes

# Live operator client
python scripts/atocore_client.py health
python scripts/atocore_client.py audit-query "gigabit" 5

API Endpoints

Method	Path	Description
POST	/ingest	Ingest markdown file or folder
POST	/query	Retrieve relevant chunks
POST	/context/build	Build full context pack
POST	/interactions	Capture prompt/response interactions
GET/POST	/memory	List/create durable memories
GET/POST	/entities	Engineering entity graph surface
GET	/admin/dashboard	Operator dashboard
GET	/health	Health check
GET	/debug/context	Inspect last context pack

API versioning

The public contract for external clients (AKC, OpenClaw, future tools) is served under a /v1 prefix. Every public endpoint is available at both its unversioned path and under /v1 — e.g. POST /entities and POST /v1/entities route to the same handler.

Rules:

• New public endpoints land at the latest version prefix.
• Backwards-compatible additions stay on the current version.
• Breaking schema changes to an existing endpoint bump the prefix (/v2/...) and leave the prior version in place until clients migrate.
• Unversioned paths are retained for internal callers (hooks, scripts, the wiki/admin UI). Do not rely on them from external clients — use /v1.

The authoritative list of versioned paths is in src/atocore/main.py (_V1_PUBLIC_PATHS). GET /openapi.json reflects both the versioned and unversioned forms.

Architecture

FastAPI (port 8100)
  |- Ingestion: markdown -> parse -> chunk -> embed -> store
  |- Retrieval: query -> embed -> vector search -> rank
  |- Context Builder: project state -> memories -> entities -> retrieval -> budget
  |- Reflection: capture -> reinforce -> extract -> triage -> promote/expire
  |- Engineering: typed entities, relationships, conflicts, wiki/mirror
  |- SQLite (documents, chunks, memories, projects, interactions, entities)
  '- ChromaDB (vector embeddings)

Configuration

Set via environment variables (prefix ATOCORE_):

Variable	Default	Description
ATOCORE_DEBUG	false	Enable debug logging
ATOCORE_PORT	8100	Server port
ATOCORE_CHUNK_MAX_SIZE	800	Max chunk size (chars)
ATOCORE_CONTEXT_BUDGET	3000	Context pack budget (chars)
ATOCORE_EMBEDDING_MODEL	paraphrase-multilingual-MiniLM-L12-v2	Embedding model
ATOCORE_RANK_PROJECT_MATCH_BOOST	2.0	Soft boost for chunks whose metadata matches the project hint
ATOCORE_RANK_PROJECT_SCOPE_FILTER	true	Filter project-hinted retrieval away from other registered project corpora
ATOCORE_RANK_PROJECT_SCOPE_CANDIDATE_MULTIPLIER	4	Widen candidate pull before project-scope filtering
ATOCORE_RANK_QUERY_TOKEN_STEP	0.08	Per-token boost when query terms appear in high-signal metadata
ATOCORE_RANK_QUERY_TOKEN_CAP	1.32	Maximum query-token boost multiplier
ATOCORE_RANK_PATH_HIGH_SIGNAL_BOOST	1.18	Boost current decision/status/requirements-like paths
ATOCORE_RANK_PATH_LOW_SIGNAL_PENALTY	0.72	Down-rank archive/history-like paths

ATOCORE_RANK_PROJECT_SCOPE_FILTER gates the hard cross-project filter only. ATOCORE_RANK_PROJECT_MATCH_BOOST remains the separate soft-ranking knob.

Testing

pip install -e ".[dev]"
pytest

Operations

• scripts/atocore_client.py provides a live API client for project refresh, project-state inspection, and retrieval-quality audits.
• scripts/retrieval_eval.py runs the live retrieval/context harness, separates blocking failures from known content gaps, and stamps JSON output with target/build metadata.
• scripts/live_status.py renders a compact read-only status report from /health, /stats, /projects, and /admin/dashboard; set ATOCORE_AUTH_TOKEN or --auth-token when those endpoints are gated.
• scripts/backfill_chunk_project_ids.py dry-runs or applies explicit project_id metadata backfills for SQLite chunks and Chroma vectors; --apply requires a confirmed Chroma snapshot.
• docs/operations.md captures the current operational priority order: retrieval quality, Wave 2 trusted-operational ingestion, AtoDrive scoping, and restore validation.
• DEV-LEDGER.md is the fast-moving source of operational truth during active development; copy claims into docs only after checking the live service.

Architecture Notes

Implementation-facing architecture notes live under docs/architecture/.

Current additions:

• docs/architecture/engineering-knowledge-hybrid-architecture.md — 5-layer hybrid model
• docs/architecture/engineering-ontology-v1.md — V1 object and relationship inventory
• docs/architecture/engineering-query-catalog.md — 20 v1-required queries
• docs/architecture/memory-vs-entities.md — canonical home split
• docs/architecture/promotion-rules.md — Layer 0 to Layer 2 pipeline
• docs/architecture/conflict-model.md — contradictory facts detection and resolution