What is hybridmind AGENTS.md?

A project instruction file for HybridMind, a local service that combines several search methods over an SQLite database and explains what it retrieved and why. It sets the rules an agent must follow before changing the code.

Understanding HybridMind’s architecture, following its cold-start steps, preserving its data indexes, running the offline test suite, and avoiding unsupported research claims.

It gives contributors a reliable starting point and helps prevent changes that conflict with the project’s architecture, research limits, or required checks.

How a3ro-dev/hybridmind configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to a3ro-dev/hybridmind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/a3ro-dev/hybridmind/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/a3ro-dev/hybridmind

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/a3ro-dev/hybridmind/agents-md/github.svg)](https://agentmods.dev/instructions/a3ro-dev/hybridmind/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/a3ro-dev/hybridmind/agents-md"><img src="https://agentmods.dev/badge/instructions/a3ro-dev/hybridmind/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/a3ro-dev/hybridmind/agents-md"><img src="https://agentmods.dev/badge/instructions/a3ro-dev/hybridmind/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,005 This file is loaded in full into every session.

When invoked 3,005 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.03005	$0.03005
Opus 5.5	$0.01202	$0.01202
Sonnet 5.5	$0.00601	$0.00601
Haiku 4.5	$0.00300	$0.00300

Measured 1mo ago against content hash a434caeb6d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hybridmind AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HybridMind — agent entry point

Updated: September 2026. Read top to bottom before changing anything; it is short on purpose. README.md is the human-facing front door; this file is the working contract for anyone editing the code.

What this is

HybridMind is a local dense + sparse + graph retrieval service for AI-memory experiments: FastAPI over an authoritative SQLite store, with FAISS HNSW, BM25/BM25S, and NetworkX indexes derived from it. It is built to show what it retrieved, why, and whether that evidence helped.

It is not a transformer KV-cache replacement and not a validated 10M–100M-token context system. Those are preregistered research targets governed by docs/RETRIEVAL_RESEARCH_PROTOCOL.md. Do not let claims drift: the honest-status table is PHASE_IMPLEMENTATION_STATUS.md, and the research evidence ledger is docs/research/design-space-experiment-program.md.

Cold start

.\.venv\Scripts\Activate.ps1            # .venv only, never system Python
pip install -r requirements.txt         # pnpm only inside memorybench/
pytest tests/ -q                        # full offline suite (~400 tests, zero provider calls)
python -m compileall -q main.py config.py api engine storage models cli sdk mcp_server scripts benchmarks tests verify

The offline suite makes zero provider calls. If your change needs one, see rule 5 below first.
make test / make compile wrap the same checks (make verify runs the legacy opt-in suite separately).
API: python -m uvicorn main:app --host 127.0.0.1 --port 8000. Startup does not wake remote providers by default.
Arriving mid-stream? Read docs/CURRENT_STATE.md (and update it when you finish; see Covenants).

Load-bearing map (do not break casually)

Path	Role	Breakage radius
`config.py`	Single configuration source of truth	Every subsystem reads it; add fields here, never raw `os.getenv`
`storage/sqlite_store.py`	Authoritative store (SQLite/WAL), bitemporal fields	Schema/write-path changes need migration thinking
`storage/vector_index.py`, `bm25_index.py`, `graph_index.py`	Derived rebuildable indexes	Must stay rebuildable-from-SQLite; never authoritative
`storage/mindfile.py`	`.mind` snapshot publish/restore validation	Security-sensitive path/checksum/semantic gates
`engine/hybrid_ranker.py`	Candidate generation, temporal filtering, RRF fusion, optional rerank stages	Retrieval semantics + measured numbers depend on exact behavior
`engine/fusion.py`	RRF (`k=60`, weight validation) plus DBSF, z-score and min-max linear fusion	Fusion contract
`engine/trisignal.py` + `api/retrieve.py`	`POST /retrieve`: independent dense/sparse/graph channels over scope-local corpora, fusion, fixed-pool rerank, evidence packing	Tri-signal semantics + measured ablations; channel independence is a contract
`engine/entity_graph.py`, `engine/entity_extraction.py`	EMG entity-memory graph (exact upstream parity) and HippoRAG-2 PPR; lexical/LLM entity extraction	Graph channel; port parity test `tests/test_emg_port_parity.py`
`eval_trisignal.py`, `benchmarks/conversational_*.py`	Engine-driven LoCoMo/LongMemEval-S ablations, official metrics, ledgers	Current valid retrieval numbers
`engine/embedding.py`, `provider_policy.py`	Remote-only native 4096-d embeddings; endpoint-bound keys	Fail-closed contract, rule 3/4
`engine/llm_client.py` (+ `llm.py`, `runpod_llm.py`)	Centralized LLM policy chain	Provider routing/spend discipline
`main.py` + `api/*.py`	App assembly, security middleware, routers	Auth/rate/limit logic lives in `main.py` ASGI middleware
`eval_ledger.py`, `eval_common.py`, `eval_stats.py`, `eval_*.py`	Evaluation ledgers, prompts, statistics	Recorded numbers must stay interpretable/comparable
`scripts/preflight.py`	Default-deny live-provider admission gate	Spend safety
`memorybench/src/providers/hybridmind/index.ts`	Benchmark harness provider (gitignored tree; these two files tracked)	Contract test: `experiments/harnesses/memorybench_provider_contract.test.ts`

Read the full file on GitHub · 188 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +9 lines · +364 tokens per session a434caeb6d88
2mo ago First seen · 179 lines · 2,641 tokens per session scan A 764f81b403b1

Subscribe to this mod's changes

hybridmind AGENTS.md is an instructions file published in the GitHub repository a3ro-dev/hybridmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,005 tokens to every session, about $0.0120 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

hybridmind AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hybridmind AGENTS.mda3ro-dev/hybridmind	Instructions file	5	1mo ago	MIT	A	3,005	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

hybridmind: Instructions file for Codex