Cymatix Context

Coordinate-index engine for LLM agents. Retrieves, weighs, and compresses your codebase into a context window — without a single LLM call on the retrieval path.

A Brick Wall Studio project. Formerly helix-context — renamed July 2026; every old surface (imports, CLI names, HELIX_* env vars, helix.toml) still works. See Migrating from helix-context.

The name comes from the engine's cymatics stage: retrieval candidates are scored against a 256-bin frequency-domain fingerprint of the query, the same way cymatics renders sound as standing-wave geometry. The /fingerprint endpoint exposes that spectrum directly.

Proof (30 seconds)

Token economics — compressor disabled (default LLM-free config), N=15 query shapes, May 2026:

In multi-turn sessions, the session delivery register elides already-seen documents — observed 37× reduction on repeated retrievals within a conversation (~40% token savings on typical multi-turn work).

Reproducer: python benchmarks/bench_rag_vs_sike_tokens.py against your own knowledge store.

External benchmark — EnterpriseRAG-Bench (Onyx, 500 questions over a ~500K-document enterprise corpus), July 2026, scored under ERB's official judge protocol and submitted to the leaderboard:

Context for those numbers: the corpus was ingested as 829,131 fragments on a single consumer desktop, and retrieval ran with zero LLM calls on the retrieval path. The claim is that operating point — local, LLM-free, at scale — not a leaderboard win. Quote the delivery and correctness numbers as a pair: gold-document delivery was 55% at 829K-fragment scale (82% at 50K) and delivery is not a graded pass — end-to-end correctness is the 41.6% above. When the gold document was delivered, the answer was correct 79% of the time, so retrieval breadth at extreme scale, not answer synthesis, is the current ceiling. Full methodology + repro: docs/benchmarks/2026-07-10-erb-blob-829k-reproduction.md.

Fusion: Reciprocal Rank Fusion has been the default ranker since 2026-07-06 — measured +12pp gold-document delivery over the legacy additive accumulator on the hardest internal bed (0.74 vs 0.62).

Agent contract: every /context response carries know { found, confidence } (grounded — you may answer) or miss { reason, escalate_to } (not found — don't answer from the knowledge store). Stale results downgrade to miss(reason="stale"|"cold"|"superseded") via the freshness gate.

Get started

Requires Python 3.11+. Core install is dependency-light (FastAPI + SQLite, no torch):

pip install cymatix-context
python -m spacy download en_core_web_sm     # ingest tagger model (with the cpu extra)

Pick extras for the features you turn on:

pip install "cymatix-context[embeddings,cpu,mcp]"   # recommended working set

Then:

# 1. Ingest your project
cymatix ingest path/to/your/project/ --recursive

# 2. One-time dense backfill (BGE-M3 vectors; retrieval is weak without it)
python scripts/backfill_bgem3_v2.py genomes/main/genome.db

# 3. Query from the CLI — no server needed
cymatix query "how does the splice step work?"

# 4. Or start the proxy for IDE / agent integration
cymatix-server            # binds to 127.0.0.1:11437
curl -s http://127.0.0.1:11437/health

Full setup (extras matrix, GPU detection, tray): docs/SETUP.md.

Usage

Three surfaces, same retrieval primitives, same JSON shapes:

# CLI — no server, no daemon, subprocess-drivable
cymatix query    "what does the splice step do?" --json
cymatix packet   "edit the splice step" --task-type edit --json
cymatix gene get abc123 --json
cymatix neighbors "splice step" --k 10 --json
cymatix refresh-targets "edit the splice step" --json
cymatix status
cymatix diag corpus

# HTTP — agent-safe packet with verified / stale_risk / refresh_targets
curl -s http://127.0.0.1:11437/context/packet \
  -H "content-type: application/json" \
  -d '{"query": "how does the freshness gate demote stale docs?"}'

Configuration lives in cymatix.toml (helix.toml still honored). Env vars use the CYMATIX_* prefix (HELIX_* still honored — explicit HELIX_* settings win over mirrored values):

CYMATIX_GENOME_PATH=genomes/dogfood/genome.db cymatix-server
CYMATIX_OTEL_ENABLED=1 CYMATIX_OTEL_ENDPOINT=localhost:4317 cymatix-server

Full CLI reference: docs/clients/cli.md. MCP tool schemas: docs/api/mcp-tools.md.

Pipeline (2 minutes)

Seven stages per turn, all LLM-free except optional splice:

  query
    │
    ▼
┌──────────────┐
│ 0. Classify  │  rule-based: decoder mode + assembly cap
└──────┬───────┘
       ▼
┌──────────────┐
│ 1. Extract   │  heuristic keyword + entity extraction
└──────┬───────┘
       ▼
┌──────────────┐  FTS5 BM25 + BGE-M3 dense (1024-dim) + tags
│ 2. Retrieve  │  + synonym expansion + co-activation + SR
│              │  + cymatics 256-bin spectrum scoring
│              │  ranked via RRF (default) or additive fusion
└──────┬───────┘
       ▼
┌──────────────┐
│ 3. Re-rank   │  CPU classifier scores (optional)
└──────┬───────┘
       ▼
┌──────────────┐
│ 4. Splice    │  Headroom Kompress (CPU) or LLM compressor
└──────┬───────┘
       ▼
┌──────────────┐  token budget + legibility headers (fired tiers,
│ 5. Assemble  │  confidence ◆/◇/⬦, compression ratio) +
│   + Stage 7  │  freshness gate (stale/cold/superseded → miss)
└──────┬───────┘  + session delivery (elide already-seen docs)
       ▼
┌──────────────┐
│ 6. Persist   │  query+response → knowledge store (background)
└──────┘───────┘
       ▼
   know { } or miss { }

• know/miss contract: know means the context is grounded, agent may answer. miss means don't answer from the knowledge store — escalate via escalate_to tools or refetch from refresh_targets.
• Caller model class: /context accepts caller_model_class: "generic" | "small_moe" | "frontier" to select render branch (ordering, assembly cap, decoder mode). See docs/api/context-endpoint.md §7.

Full reference: docs/config-reference.md.

Core retrieval:

Ingestion + maintenance:

Identity + sessions:

Diagnostics:

Full schema: docs/api/endpoints.md.

Canonical import package is cymatix_context; helix_context remains as an alias shim (identical module objects). Module-level shims genome.py, ribosome.py, server.py, replication.py, hgt.py also persist. Lexicon: docs/ROSETTA.md.

IDE + MCP integration

{
  "mcpServers": {
    "cymatix-context": {
      "command": "python",
      "args": ["-m", "cymatix_context.mcp_server"],
      "cwd": "/absolute/path/to/your/project",
      "env": { "CYMATIX_MCP_URL": "http://127.0.0.1:11437" }
    }
  }
}

The server self-identifies as cymatix, so client tools appear as mcp__cymatix__*. Configs written for the helix era keep working if you leave -m helix_context.mcp_server and HELIX_MCP_URL in place.

models:
  - name: Cymatix (Local)
    provider: openai
    model: gemma3:e4b
    apiBase: http://127.0.0.1:11437/v1
    apiKey: EMPTY
    roles: [chat]
    defaultCompletionOptions:
      contextLength: 128000
      maxTokens: 4096

Use Chat mode, not Agent mode — the proxy doesn't handle tool routing.

OPENAI_BASE_URL=http://localhost:11437/v1 your-app

Knowledge store management

[genome]
path = "genomes/main/genome.db"   # relative to the cymatix run directory

Backup (safe while running — WAL mode):

cp genomes/main/genome.db backups/genome-$(date +%Y%m%d).db

BGE-M3 backfill (one-time, after install):

python scripts/backfill_bgem3_v2.py genomes/main/genome.db

Observability

scripts\setup-grafana-telem.ps1     # Windows
scripts/setup-grafana-telem.sh      # Linux / macOS

Dashboard: http://localhost:3000/d/helix-overview. Full surface: docs/architecture/OBSERVABILITY.md.

Migrating from helix-context

Everything old keeps working for a deprecation window; new names are canonical.

The knowledge-store file format is unchanged — existing genome.db files work as-is, no re-ingest needed.

Gotchas

• Knowledge store path is genomes/main/genome.db (not project root). Delete to start fresh.
• BGE-M3 backfill is one-time post-install — embedding_dense_v2 IS NULL until you run scripts/backfill_bgem3_v2.py. Low retrieval rate without it.
• Fusion mode defaults to "rrf" (since 2026-07-06; +12pp gold delivery vs additive on the hardest bed). "additive" remains as the legacy accumulator, scheduled for condition-gated removal. Under RRF the abstain gates run ratio-only.
• Session delivery (session_delivery_enabled = true) tracks delivered docs per session, elides repeats. ~40% token savings on multi-turn. Pass ignore_delivered: true in /context body for benchmarks.
• know/miss contract requires the agent prompt fragment to be honored — without it, frontier models confabulate. Import cymatix_context.agent_prompt.full_fragment().
• Naming lexicon: biology terms (gene, genome, ribosome) have canonical software equivalents (document, knowledge store, compressor). Both work in code; new code uses software terms. See docs/ROSETTA.md.

Testing

python -m pytest tests/ -m "not live" -v   # ~2,900 tests, no external services

Documentation

Acknowledgments

Built on: spaCy NER · Howard 2005 TCM · Stachenfeld 2017 SR · SQLite FTS5 BM25 · BGE-M3 · Kompress · Headroom

License

Apache-2.0. See NOTICE for third-party attributions. Cymatix Context is a Brick Wall Studio project by Michael Bachaud.