cogno-engram 0.1.0__tar.gz

cogno_engram-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Sudoers AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cogno_engram-0.1.0/PKG-INFO

@@ -0,0 +1,206 @@
+Metadata-Version: 2.4
+Name: cogno-engram
+Version: 0.1.0
+Summary: Persistence substrate for the Cogno cognitive pipeline — memory store, knowledge graph, conversation buffer, and sleep-time consolidation (hypnos)
+Author: Vinicius Vale
+Maintainer: Sudoers AI
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/sudoers-ai/cogno-engram
+Project-URL: Repository, https://github.com/sudoers-ai/cogno-engram
+Project-URL: Issues, https://github.com/sudoers-ai/cogno-engram/issues
+Keywords: llm,memory,rag,knowledge-graph,pgvector,redis,agents,consolidation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Operating System :: OS Independent
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: mypy>=1.8; extra == "dev"
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary,pool]>=3.1; extra == "postgres"
+Requires-Dist: pgvector>=0.2; extra == "postgres"
+Provides-Extra: redis
+Requires-Dist: redis>=5.0; extra == "redis"
+Dynamic: license-file
+
+# cogno-engram
+
+**Persistence substrate for the [Cogno](https://github.com/sudoers-ai/cogno-anima) cognitive pipeline** — memory store, knowledge graph, conversation buffer, and sleep-time consolidation.
+
+`cogno-engram` is the *memory* to [`cogno-anima`](https://github.com/sudoers-ai/cogno-anima)'s *mind*. Where `cogno-anima` is pure, infrastructure-agnostic cognition (no I/O), `cogno-engram` is the opinionated **substrate** that remembers: it persists conversation turns, consolidates them into long-term semantic memories, and threads them into a relational knowledge graph.
+
+> Status: **alpha** — the contract (ports + types) and the zero-dependency in-memory adapter are in place. The Postgres/Redis reference adapters and the LLM-driven consolidation tiers are in build-out.
+
+## Philosophy: ports, not a universal store
+
+A single abstraction over relational + key-value + graph collapses to a lowest-common-denominator that throws away vector search and graph traversal. Instead, `cogno-engram` defines **three capability-scoped ports**, each backed by the storage engine that fits it:
+
+| Port | Shape | Reference adapter |
+| --- | --- | --- |
+| `MemoryStore` | sessions / turns / memories + hybrid retrieval + per-turn traces | Postgres + pgvector |
+| `ConversationBuffer` | sliding short-term window (+ TTL) | Redis |
+| `KnowledgeGraph` | typed nodes + directed edges + multi-hop walk | Postgres (recursive CTE) |
+
+Vector search is an **optional capability** (`SupportsVectorSearch`) — a store without it degrades retrieval to lexical/chronological instead of breaking.
+
+## Decoupled by an opaque `scope`
+
+Every row is isolated by an opaque `scope` string. `cogno-engram` never interprets it — the **host** composes it (e.g. `"tenant/phone"`) and owns its meaning and any cross-scope aggregation. There is no `tenant_id`/`phone_id` in the schema; the substrate is reusable for any domain.
+
+```python
+from cogno_engram import InMemoryStore, MemoryRecord, RetrievalQuery
+
+store = InMemoryStore()
+session = await store.create_session(scope="acme/phone1")
+await store.save_memory(MemoryRecord("acme/phone1", "preference", "likes oat milk", embedding=[...]))
+
+hits = await store.load_memories(
+    "acme/phone1",
+    query=RetrievalQuery(text="what milk?", embedding=[...]),   # hybrid: vector + lexical + feedback
+)
+```
+
+## `hypnos` — sleep-time consolidation (3-tier)
+
+Named for the god of sleep: consolidation runs while a session "sleeps". As everywhere in Cogno, **engram provides the steps, the host runs the loop** — there is no daemon here.
+
+- **Tier 1 — `micro_consolidate`** — synchronous, per-turn, **LLM-free** (goal transitions, sentiment spikes, PII leaks, new-domain interest).
+- **Tier 2 — `periodic_consolidate`** — async, every N turns, LLM extraction (+ KG relations).
+- **Tier 3 — `consolidate_session`** — async, on session close/idle, holistic LLM pass (+ feedback-driven KG pruning).
+
+## Install
+
+```bash
+pip install cogno-engram                 # core: ports + in-memory adapter (zero deps)
+pip install "cogno-engram[postgres]"     # Postgres + pgvector adapter
+pip install "cogno-engram[redis]"        # Redis buffer adapter
+```
+
+The Tier-2/3 consolidation drives an LLM through a `cogno-anima` `LLMBackend` (host-injected).
+
+## Postgres + pgvector adapter
+
+The reference adapter implements `MemoryStore` (hybrid retrieval = `0.60·vector + 0.40·BM25 + 0.05·feedback`) and `KnowledgeGraph` (recursive-CTE multi-hop walk) over one database. Call `ensure_schema` once for the idempotent DDL (tables + indexes; no alembic required — re-running it additively creates any new table via `CREATE TABLE IF NOT EXISTS`):
+
+The high-volume tables (`turns`, `memories`, `turn_traces`) opt into `HASH(scope)` partitioning. `turn_traces` is a dedicated table holding one **opaque JSONB** trace per turn (`save_turn_trace` / `traces_for_session`) — the host composes it (e.g. the pipeline's NER/EGO signals for an audit view); engram never interprets it.
+
+```python
+import psycopg
+from cogno_engram.adapters.postgres import PostgresStore, ensure_schema
+
+async with await psycopg.AsyncConnection.connect(dsn, autocommit=True) as conn:
+    await ensure_schema(conn)                 # CREATE TABLE/INDEX IF NOT EXISTS
+
+store = PostgresStore(dsn=dsn, mask_pii=True)
+hits = await store.load_memories("acme/phone1", query=RetrievalQuery(text="...", embedding=[...]))
+```
+
+For scale, opt the high-volume tables into HASH(scope) partitioning (the generic
+equivalent of the parent's LIST(tenant), with zero DDL per new scope):
+
+```python
+await ensure_schema(conn, partition_by_scope=True, partitions=8)
+```
+
+## Maintenance (sleep-time upkeep)
+
+Like `hypnos`, the host schedules; engram does the work — keeping the substrate
+bounded and consistent over time:
+
+```python
+from cogno_engram import maintenance
+
+await maintenance.prune_memories(store, scope, older_than=timedelta(days=180), max_confidence=0.75)
+await maintenance.reembed_memories(store, embedder, scope)      # after an embedding-model change
+await maintenance.prune_orphan_nodes(kg, scope)                 # drop edgeless graph nodes
+```
+
+## Reranking
+
+`load_memories` returns relevance-ordered candidates; `rerank` refines them with a two-pass pipeline before you inject the top-k:
+
+```python
+from cogno_engram import rerank, RerankConfig
+
+candidates = await store.load_memories("acme/phone1", query=q, limit=20)
+top = rerank(candidates, query_text=q.text, top_k=5)   # sim + recency-decay + category boost
+```
+
+Pass 1 is pure (`sim·0.60 + recency·0.25 + category·0.15`, half-life and boosts configurable via `RerankConfig`). Pass 2 is an optional **host-injected** cross-encoder callable `(query, [content]) -> [score]` — so cogno-engram ships no heavy ML dependency.
+
+## EngramBench
+
+A self-contained quality harness (no DB, no model — deterministic) over the in-memory adapter, scoring the substrate's three jobs:
+
+```bash
+python3 cognobench.py                 # 5 deterministic dims: retrieval/buffer/consolidation/graph/lifecycle
+python3 cognobench.py --only graph
+python3 cognobench.py --min-score 100 # CI gate
+# opt-in, model-dependent: hypnos Tier-2 extraction quality vs a real Ollama model
+python3 cognobench.py --only llm_consolidation
+# opt-in: the FULL edge-capture path (Tier-2 relation extraction → graph at kg_scope)
+python3 cognobench.py --only graph_capture --model mistral:latest
+# visualize every graph the bench built/captured as one self-contained HTML
+python3 cognobench.py --only graph graph_capture --graph-html graphs.html
+```
+
+Dimensions: **retrieval** (hit@1, vector + BM25-only), **buffer** (sliding-window
+retention), **consolidation** (Tier-1 micro), **graph** (multi-hop walk),
+**lifecycle** (end-to-end: turns → Tier-1 → retrieval+rerank), and the opt-in
+**llm_consolidation** (Tier-2 memory quality against Ollama) and **graph_capture**
+(Tier-2 relation extraction against Ollama: hard invariants — no dangling edges,
+valid confidence, session-tagged, graph rows only at `kg_scope` — plus soft
+entity-connectivity checks). Case distributions are modelled on the parent's real
+data (goal-heavy memories, BM25-dominant retrieval, NEEDS/PREFERS graph) — all
+synthetic.
+
+## The Cogno ecosystem
+
+`cogno-engram` is one organ of **[Cogno](https://github.com/sudoers-ai)** — a family of
+small, composable, Apache-2.0 libraries that together form a complete
+conversational-agent platform. Each library owns a single concern and stays
+infra-agnostic; a **host** assembles them into a running agent:
+
+![The Cogno ecosystem](docs/assets/cogno-ecosystem.svg)
+
+The open-source libraries are the organs; the **host is the body** that joins
+them. Our reference host — `cogno-host`, with its `cogno-ui` dashboard — is the
+private product layer, but it holds no special powers: everything it does rides
+on the public seams documented in each library's `docs/HOST_INTEGRATION.md`, so
+you can assemble a body of your own.
+
+## Testing
+
+```bash
+pip install -e ".[dev]"
+python3 -m pytest -q                   # unit + bench-smoke (Postgres tests auto-skip)
+
+# Run the integration suites against real services:
+docker run -d --rm --name engram-pg -e POSTGRES_PASSWORD=postgres \
+    -p 55432:5432 pgvector/pgvector:pg16
+docker run -d --rm --name engram-redis -p 56379:6379 redis:7-alpine
+ENGRAM_TEST_DSN=postgresql://postgres:postgres@localhost:55432/postgres \
+ENGRAM_TEST_REDIS_URL=redis://localhost:56379/0 \
+    python3 -m pytest tests/test_postgres_integration.py tests/test_redis_integration.py -q
+```
+
+## What lives in the host (not here)
+
+Business identity (`tenants`/`identities`), billing/token ledgers, persona/domain schemas, feedback *capture* (emoji → ±1), persona switching, OTP/rate-limiting, and the consolidation **worker loop**. `cogno-engram` only knows `scope`, sessions/turns/memories, the graph, and the buffer.
+
+## License
+
+Apache-2.0 © Sudoers AI

cogno_engram-0.1.0/README.md

@@ -0,0 +1,168 @@
+# cogno-engram
+
+**Persistence substrate for the [Cogno](https://github.com/sudoers-ai/cogno-anima) cognitive pipeline** — memory store, knowledge graph, conversation buffer, and sleep-time consolidation.
+
+`cogno-engram` is the *memory* to [`cogno-anima`](https://github.com/sudoers-ai/cogno-anima)'s *mind*. Where `cogno-anima` is pure, infrastructure-agnostic cognition (no I/O), `cogno-engram` is the opinionated **substrate** that remembers: it persists conversation turns, consolidates them into long-term semantic memories, and threads them into a relational knowledge graph.
+
+> Status: **alpha** — the contract (ports + types) and the zero-dependency in-memory adapter are in place. The Postgres/Redis reference adapters and the LLM-driven consolidation tiers are in build-out.
+
+## Philosophy: ports, not a universal store
+
+A single abstraction over relational + key-value + graph collapses to a lowest-common-denominator that throws away vector search and graph traversal. Instead, `cogno-engram` defines **three capability-scoped ports**, each backed by the storage engine that fits it:
+
+| Port | Shape | Reference adapter |
+| --- | --- | --- |
+| `MemoryStore` | sessions / turns / memories + hybrid retrieval + per-turn traces | Postgres + pgvector |
+| `ConversationBuffer` | sliding short-term window (+ TTL) | Redis |
+| `KnowledgeGraph` | typed nodes + directed edges + multi-hop walk | Postgres (recursive CTE) |
+
+Vector search is an **optional capability** (`SupportsVectorSearch`) — a store without it degrades retrieval to lexical/chronological instead of breaking.
+
+## Decoupled by an opaque `scope`
+
+Every row is isolated by an opaque `scope` string. `cogno-engram` never interprets it — the **host** composes it (e.g. `"tenant/phone"`) and owns its meaning and any cross-scope aggregation. There is no `tenant_id`/`phone_id` in the schema; the substrate is reusable for any domain.
+
+```python
+from cogno_engram import InMemoryStore, MemoryRecord, RetrievalQuery
+
+store = InMemoryStore()
+session = await store.create_session(scope="acme/phone1")
+await store.save_memory(MemoryRecord("acme/phone1", "preference", "likes oat milk", embedding=[...]))
+
+hits = await store.load_memories(
+    "acme/phone1",
+    query=RetrievalQuery(text="what milk?", embedding=[...]),   # hybrid: vector + lexical + feedback
+)
+```
+
+## `hypnos` — sleep-time consolidation (3-tier)
+
+Named for the god of sleep: consolidation runs while a session "sleeps". As everywhere in Cogno, **engram provides the steps, the host runs the loop** — there is no daemon here.
+
+- **Tier 1 — `micro_consolidate`** — synchronous, per-turn, **LLM-free** (goal transitions, sentiment spikes, PII leaks, new-domain interest).
+- **Tier 2 — `periodic_consolidate`** — async, every N turns, LLM extraction (+ KG relations).
+- **Tier 3 — `consolidate_session`** — async, on session close/idle, holistic LLM pass (+ feedback-driven KG pruning).
+
+## Install
+
+```bash
+pip install cogno-engram                 # core: ports + in-memory adapter (zero deps)
+pip install "cogno-engram[postgres]"     # Postgres + pgvector adapter
+pip install "cogno-engram[redis]"        # Redis buffer adapter
+```
+
+The Tier-2/3 consolidation drives an LLM through a `cogno-anima` `LLMBackend` (host-injected).
+
+## Postgres + pgvector adapter
+
+The reference adapter implements `MemoryStore` (hybrid retrieval = `0.60·vector + 0.40·BM25 + 0.05·feedback`) and `KnowledgeGraph` (recursive-CTE multi-hop walk) over one database. Call `ensure_schema` once for the idempotent DDL (tables + indexes; no alembic required — re-running it additively creates any new table via `CREATE TABLE IF NOT EXISTS`):
+
+The high-volume tables (`turns`, `memories`, `turn_traces`) opt into `HASH(scope)` partitioning. `turn_traces` is a dedicated table holding one **opaque JSONB** trace per turn (`save_turn_trace` / `traces_for_session`) — the host composes it (e.g. the pipeline's NER/EGO signals for an audit view); engram never interprets it.
+
+```python
+import psycopg
+from cogno_engram.adapters.postgres import PostgresStore, ensure_schema
+
+async with await psycopg.AsyncConnection.connect(dsn, autocommit=True) as conn:
+    await ensure_schema(conn)                 # CREATE TABLE/INDEX IF NOT EXISTS
+
+store = PostgresStore(dsn=dsn, mask_pii=True)
+hits = await store.load_memories("acme/phone1", query=RetrievalQuery(text="...", embedding=[...]))
+```
+
+For scale, opt the high-volume tables into HASH(scope) partitioning (the generic
+equivalent of the parent's LIST(tenant), with zero DDL per new scope):
+
+```python
+await ensure_schema(conn, partition_by_scope=True, partitions=8)
+```
+
+## Maintenance (sleep-time upkeep)
+
+Like `hypnos`, the host schedules; engram does the work — keeping the substrate
+bounded and consistent over time:
+
+```python
+from cogno_engram import maintenance
+
+await maintenance.prune_memories(store, scope, older_than=timedelta(days=180), max_confidence=0.75)
+await maintenance.reembed_memories(store, embedder, scope)      # after an embedding-model change
+await maintenance.prune_orphan_nodes(kg, scope)                 # drop edgeless graph nodes
+```
+
+## Reranking
+
+`load_memories` returns relevance-ordered candidates; `rerank` refines them with a two-pass pipeline before you inject the top-k:
+
+```python
+from cogno_engram import rerank, RerankConfig
+
+candidates = await store.load_memories("acme/phone1", query=q, limit=20)
+top = rerank(candidates, query_text=q.text, top_k=5)   # sim + recency-decay + category boost
+```
+
+Pass 1 is pure (`sim·0.60 + recency·0.25 + category·0.15`, half-life and boosts configurable via `RerankConfig`). Pass 2 is an optional **host-injected** cross-encoder callable `(query, [content]) -> [score]` — so cogno-engram ships no heavy ML dependency.
+
+## EngramBench
+
+A self-contained quality harness (no DB, no model — deterministic) over the in-memory adapter, scoring the substrate's three jobs:
+
+```bash
+python3 cognobench.py                 # 5 deterministic dims: retrieval/buffer/consolidation/graph/lifecycle
+python3 cognobench.py --only graph
+python3 cognobench.py --min-score 100 # CI gate
+# opt-in, model-dependent: hypnos Tier-2 extraction quality vs a real Ollama model
+python3 cognobench.py --only llm_consolidation
+# opt-in: the FULL edge-capture path (Tier-2 relation extraction → graph at kg_scope)
+python3 cognobench.py --only graph_capture --model mistral:latest
+# visualize every graph the bench built/captured as one self-contained HTML
+python3 cognobench.py --only graph graph_capture --graph-html graphs.html
+```
+
+Dimensions: **retrieval** (hit@1, vector + BM25-only), **buffer** (sliding-window
+retention), **consolidation** (Tier-1 micro), **graph** (multi-hop walk),
+**lifecycle** (end-to-end: turns → Tier-1 → retrieval+rerank), and the opt-in
+**llm_consolidation** (Tier-2 memory quality against Ollama) and **graph_capture**
+(Tier-2 relation extraction against Ollama: hard invariants — no dangling edges,
+valid confidence, session-tagged, graph rows only at `kg_scope` — plus soft
+entity-connectivity checks). Case distributions are modelled on the parent's real
+data (goal-heavy memories, BM25-dominant retrieval, NEEDS/PREFERS graph) — all
+synthetic.
+
+## The Cogno ecosystem
+
+`cogno-engram` is one organ of **[Cogno](https://github.com/sudoers-ai)** — a family of
+small, composable, Apache-2.0 libraries that together form a complete
+conversational-agent platform. Each library owns a single concern and stays
+infra-agnostic; a **host** assembles them into a running agent:
+
+![The Cogno ecosystem](docs/assets/cogno-ecosystem.svg)
+
+The open-source libraries are the organs; the **host is the body** that joins
+them. Our reference host — `cogno-host`, with its `cogno-ui` dashboard — is the
+private product layer, but it holds no special powers: everything it does rides
+on the public seams documented in each library's `docs/HOST_INTEGRATION.md`, so
+you can assemble a body of your own.
+
+## Testing
+
+```bash
+pip install -e ".[dev]"
+python3 -m pytest -q                   # unit + bench-smoke (Postgres tests auto-skip)
+
+# Run the integration suites against real services:
+docker run -d --rm --name engram-pg -e POSTGRES_PASSWORD=postgres \
+    -p 55432:5432 pgvector/pgvector:pg16
+docker run -d --rm --name engram-redis -p 56379:6379 redis:7-alpine
+ENGRAM_TEST_DSN=postgresql://postgres:postgres@localhost:55432/postgres \
+ENGRAM_TEST_REDIS_URL=redis://localhost:56379/0 \
+    python3 -m pytest tests/test_postgres_integration.py tests/test_redis_integration.py -q
+```
+
+## What lives in the host (not here)
+
+Business identity (`tenants`/`identities`), billing/token ledgers, persona/domain schemas, feedback *capture* (emoji → ±1), persona switching, OTP/rate-limiting, and the consolidation **worker loop**. `cogno-engram` only knows `scope`, sessions/turns/memories, the graph, and the buffer.
+
+## License
+
+Apache-2.0 © Sudoers AI

cogno_engram-0.1.0/cogno_engram/__init__.py

@@ -0,0 +1,43 @@
+"""cogno-engram — persistence substrate for the Cogno cognitive pipeline."""
+
+from cogno_engram import hypnos, maintenance
+from cogno_engram.adapters.in_memory import InMemoryBuffer, InMemoryGraph, InMemoryStore
+from cogno_engram.graph_context import format_graph_context, ingest_entities
+from cogno_engram.reranker import RerankConfig, recency_score, rerank
+from cogno_engram.ports import (
+    ConversationBuffer,
+    KnowledgeGraph,
+    MemoryStore,
+    SupportsVectorSearch,
+)
+from cogno_engram.types import (
+    DEFAULT_CONFIDENCE,
+    VALID_NODE_TYPES,
+    GraphEdge,
+    GraphNode,
+    HybridWeights,
+    MemoryRecord,
+    NodeContext,
+    RetrievalQuery,
+    Session,
+    SessionSummary,
+    TurnRecord,
+    TurnTrace,
+)
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "__version__",
+    # ports
+    "MemoryStore", "SupportsVectorSearch", "ConversationBuffer", "KnowledgeGraph",
+    # types
+    "Session", "TurnRecord", "TurnTrace", "MemoryRecord", "GraphNode", "GraphEdge", "NodeContext",
+    "RetrievalQuery", "HybridWeights", "SessionSummary",
+    "DEFAULT_CONFIDENCE", "VALID_NODE_TYPES",
+    # reference adapters
+    "InMemoryStore", "InMemoryBuffer", "InMemoryGraph",
+    # consolidation + maintenance + reranking + graph helpers
+    "hypnos", "maintenance", "rerank", "RerankConfig", "recency_score",
+    "ingest_entities", "format_graph_context",
+]

cogno_engram-0.1.0/cogno_engram/adapters/__init__.py

@@ -0,0 +1,3 @@
+from cogno_engram.adapters.in_memory import InMemoryBuffer, InMemoryGraph, InMemoryStore
+
+__all__ = ["InMemoryStore", "InMemoryBuffer", "InMemoryGraph"]