talamus 1.0.0__tar.gz

talamus-1.0.0/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 [yyyy] [name of copyright owner]
+
+   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.

talamus-1.0.0/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.4
+Name: talamus
+Version: 1.0.0
+Summary: Local-first knowledge compiler with graph-first retrieval for AI agents.
+Author: Talamus Contributors
+License: Apache-2.0
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: docling
+Requires-Dist: docling>=2.0; extra == "docling"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0; extra == "mcp"
+Provides-Extra: dev
+Requires-Dist: ruff>=0.6; extra == "dev"
+Requires-Dist: mypy>=1.11; extra == "dev"
+Provides-Extra: bench
+Requires-Dist: tiktoken>=0.7; extra == "bench"
+Requires-Dist: rank-bm25>=0.2; extra == "bench"
+Requires-Dist: faiss-cpu>=1.8; extra == "bench"
+Requires-Dist: sentence-transformers>=3.0; extra == "bench"
+Requires-Dist: mem0ai>=0.1; extra == "bench"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9; extra == "docs"
+Provides-Extra: ui
+Requires-Dist: fastapi>=0.110; extra == "ui"
+Requires-Dist: uvicorn>=0.29; extra == "ui"
+Requires-Dist: pywebview>=5.0; extra == "ui"
+Provides-Extra: pdf
+Requires-Dist: pypdf>=4; extra == "pdf"
+Dynamic: license-file
+
+# Talamus
+
+[![CI](https://github.com/GCrapuzzi/Talamus-Wiki/actions/workflows/ci.yml/badge.svg)](https://github.com/GCrapuzzi/Talamus-Wiki/actions/workflows/ci.yml) ![license](https://img.shields.io/badge/license-Apache--2.0-blue) ![python](https://img.shields.io/badge/python-3.11%2B-blue)
+
+**Local-first memory with time, meaning, and verifiability — for your second brain and your AI agents.**
+
+Talamus compiles your sources (documents, notes, and agent work sessions) into
+**source-grounded, cross-linked concept notes**, builds a typed **graph as an
+index**, and answers questions **with citations** — all on your machine, on the
+LLM engine you already use.
+
+<!-- demo GIF goes here: talamus demo → search → read -->
+
+> Markdown notes you can edit in Obsidian · a graph that routes retrieval ·
+> provenance on every claim · usable from the CLI, the SDK, and MCP.
+
+## Why Talamus
+
+Most "AI memory" is either a pile of vector chunks (no structure, no provenance)
+or a cloud service (your knowledge leaves your machine). Talamus is built on three
+properties that, **together**, nothing else gives you:
+
+- **TIME** — a bitemporal model: contradictions *invalidate* old facts instead of
+  deleting them — `talamus timeline`, `ask --as-of 2026-01`. *(shipped: transaction
+  history + valid-time claim overlay)*
+- **MEANING** — a typed, **self-emerging ontology**: free-form relation surfaces
+  the fixed types can't explain are induced into *candidate types*, reviewed,
+  promoted, versioned — and measurably improve retrieval (`talamus ontology`).
+  *(shipped: fixed types + Ontology Lab; experimental: emergent schema at scale)*
+- **VERIFIABILITY** — every note keeps its **sources**; verify single notes or in
+  batch, with proposed corrections going through a review queue (`talamus verify
+  --all`). *(shipped)*
+
+Plus a wedge the others don't optimize for: **memory for agents** that need
+current, cited, reasoned truth.
+
+## Talamus vs the alternatives
+
+|                                   | Plain RAG | llm_wiki            | Zep / mem0 | **Talamus**       |
+| --------------------------------- | --------- | ------------------- | ---------- | ----------------- |
+| Local-first                       | varies    | ✅                  | ❌ cloud   | ✅                |
+| Human-editable notes (Obsidian)   | ❌        | ✅                  | ❌         | ✅                |
+| Typed ontology for reasoning      | ❌        | ❌ statistical graph | partial    | ✅                |
+| Keeps history / "truth at time T" | ❌        | ❌ overwrites        | partial    | ✅ *(MVP)*        |
+| Provenance + correct-from-source  | ❌        | tracking only       | partial    | ✅                |
+| Agent memory (read + write, MCP)  | ❌        | partial             | ✅         | ✅                |
+
+## Quickstart
+
+```bash
+pipx install talamus            # or: pip install talamus
+
+talamus demo                    # try a small example brain instantly (no LLM)
+talamus search "embedding"
+
+talamus init                    # your own brain (auto-detects your LLM engine)
+talamus ingest report.pdf       # PDF / DOCX / HTML / Markdown / URL -> linked concept-notes
+talamus import-vault ~/vault    # coming from Obsidian/Notion? 1:1 import, zero LLM cost
+talamus ask "how does X work?"  # cited answer
+talamus ui                      # optional web workbench (pip install talamus[ui])
+```
+
+Run `talamus` with no arguments for a status panel, or follow the
+**[10-minute quickstart](docs/quickstart.md)**.
+
+## Choose your engine
+
+Talamus runs on what you already have — set it in `talamus.json` or `TALAMUS_LLM_PROVIDER`:
+
+- `claude-cli` — your Claude subscription (default if `claude` is on PATH)
+- `codex-cli` — your ChatGPT subscription (Codex is bundled with it)
+- `gemini-cli` — your Gemini subscription
+- `opencode` — opencode, with whatever providers you configured in it
+- `antigravity-cli` — Google Antigravity (`agy`)
+- `ollama` — a local model, fully offline (`TALAMUS_LLM_MODEL=llama3`)
+- `anthropic-api` — the Anthropic API (`ANTHROPIC_API_KEY`)
+
+Every engine gets per-task **model+effort tiering** automatically: bulk work
+(extraction, routing) runs on the cheap tier, the answer you read on the strong
+one — top quality while burning as little of your subscription as possible.
+
+## For agents (MCP)
+
+```bash
+talamus mcp install             # writes .mcp.json for Claude Code / Cursor / Desktop
+talamus hook                    # prints a SessionEnd hook to auto-capture your work
+```
+
+Agents `search` / `read_note` / `recall` / `overview` / `neighbors` to read the brain,
+and `remember` to grow it. The graph is an **index, not the answer** — agents read the
+real notes and cite them.
+
+## Browse it like a wiki
+
+Open `notes/` as an Obsidian vault: notes cross-link with `[[wikilinks]]`, so you
+navigate the knowledge by hovering and clicking. Prefer a dedicated app?
+**`talamus ui`** — the local web workbench (`pip install talamus[ui]`) — gives you
+chat, search, clickable wikilinks, graph navigation, and domain browsing.
+
+## How it works
+
+Sources (Markdown, text, **PDF, DOCX, HTML, URLs**) are normalized and preserved; an
+LLM extracts atomic **concept notes** (with sources, typed relations, and wikilinks);
+Talamus builds rebuildable indexes (graph + BM25 + ontology) and a hierarchical
+**domain overview**. Retrieval routes through the overview, then **reranks** a union of
+graph + BM25 candidates, and fits the context to a **token budget** so answer cost stays
+flat as the brain grows. Answers cite the notes they used, and `talamus eval` measures
+retrieval quality (recall@k / MRR) so changes are judged by numbers, not vibes.
+
+Storage is **hybrid**: `notes/*.md` is the human-editable view (Obsidian-compatible),
+`.talamus/cache/` holds the machine truth (provenance) and the derived indexes;
+`talamus reindex` folds your hand-edits back in. The core is **Python stdlib-only**;
+extras (MCP, engines) are optional. See **[architecture](docs/architecture.md)**.
+
+## How it compares (measured)
+
+A real head-to-head against a dense vector-DB RAG pipeline (sentence-transformers
++ FAISS) and vanilla BM25, same corpus/queries/judgments
+([details](dev/research/2026-06-rs5-competitive-shootout.md)):
+
+| corpus | metric | Talamus | BM25 | Vector DB |
+|---|---|---|---|---|
+| BEIR SciFact (English, dense's turf) | recall@10 | 0.776 | 0.776 | 0.783 |
+| BEIR SciFact | hit@10 | 0.793 | 0.797 | 0.793 |
+| Cross-language + vague (our turf) | recall@10 | **0.886** | 0.771 | 0.700 |
+| Cross-language + vague | hit@10 | **0.971** | 0.829 | 0.743 |
+
+**On the vector DB's home turf we tie it — with zero embedding infrastructure.
+On cross-language and vague queries we win decisively** (the dense model lands
+last). Plus time, meaning and verifiability (100% of notes source-resolvable;
+97.7% fewer tokens than loading the brain) — moats no vector DB has.
+
+## Use cases
+
+- **Second brain** — compile your reading and notes into a connected, cited wiki.
+- **Agent memory** — give your agents a local, structured, verifiable memory they
+  can both read and grow.
+
+## Status & roadmap
+
+**Shipped** (tested, gate-green): the sources → notes → cited-answers loop;
+**multi-brain** with a federated read index (`brains`, `--all-brains`); **repo scan**
+with dry-run, secret redaction and resumable jobs (`scan`, `jobs`); **persistent
+indexes** (sqlite/FTS5 — search p95 at 10.000 notes: **34 ms**); the **Ontology Lab**
+(emergent relation types: induce → review → promote, with measured retrieval lift);
+the **temporal model** (`timeline`, `ask --as-of`); **batch verification** with a
+review queue; multi-format ingestion (PDF/DOCX/HTML/URL); the CLI dashboard; the
+**MCP server** (read+write with explicit scopes); the **UI workbench** (11 views,
+`talamus ui [--web]`).
+
+**Experimental**: emergent-schema quality at large scale (metrics built-in:
+`ontology eval`/`stability`); UI runtime polish (smoke-tested headless, verify
+rendering with `talamus ui`).
+
+**Roadmap** ([details](dev/STATE.md)): OCR &
+more formats (PPTX/XLSX/EPUB/media), packaged installers, remote
+authenticated MCP, synonym-merge for emergent types, graph canvas view.
+
+## Development
+
+```bash
+pip install -e ".[dev,mcp]"
+python dev.py                    # lint + types + tests
+```
+
+## License
+
+Apache-2.0.

talamus-1.0.0/README.md

@@ -0,0 +1,168 @@
+# Talamus
+
+[![CI](https://github.com/GCrapuzzi/Talamus-Wiki/actions/workflows/ci.yml/badge.svg)](https://github.com/GCrapuzzi/Talamus-Wiki/actions/workflows/ci.yml) ![license](https://img.shields.io/badge/license-Apache--2.0-blue) ![python](https://img.shields.io/badge/python-3.11%2B-blue)
+
+**Local-first memory with time, meaning, and verifiability — for your second brain and your AI agents.**
+
+Talamus compiles your sources (documents, notes, and agent work sessions) into
+**source-grounded, cross-linked concept notes**, builds a typed **graph as an
+index**, and answers questions **with citations** — all on your machine, on the
+LLM engine you already use.
+
+<!-- demo GIF goes here: talamus demo → search → read -->
+
+> Markdown notes you can edit in Obsidian · a graph that routes retrieval ·
+> provenance on every claim · usable from the CLI, the SDK, and MCP.
+
+## Why Talamus
+
+Most "AI memory" is either a pile of vector chunks (no structure, no provenance)
+or a cloud service (your knowledge leaves your machine). Talamus is built on three
+properties that, **together**, nothing else gives you:
+
+- **TIME** — a bitemporal model: contradictions *invalidate* old facts instead of
+  deleting them — `talamus timeline`, `ask --as-of 2026-01`. *(shipped: transaction
+  history + valid-time claim overlay)*
+- **MEANING** — a typed, **self-emerging ontology**: free-form relation surfaces
+  the fixed types can't explain are induced into *candidate types*, reviewed,
+  promoted, versioned — and measurably improve retrieval (`talamus ontology`).
+  *(shipped: fixed types + Ontology Lab; experimental: emergent schema at scale)*
+- **VERIFIABILITY** — every note keeps its **sources**; verify single notes or in
+  batch, with proposed corrections going through a review queue (`talamus verify
+  --all`). *(shipped)*
+
+Plus a wedge the others don't optimize for: **memory for agents** that need
+current, cited, reasoned truth.
+
+## Talamus vs the alternatives
+
+|                                   | Plain RAG | llm_wiki            | Zep / mem0 | **Talamus**       |
+| --------------------------------- | --------- | ------------------- | ---------- | ----------------- |
+| Local-first                       | varies    | ✅                  | ❌ cloud   | ✅                |
+| Human-editable notes (Obsidian)   | ❌        | ✅                  | ❌         | ✅                |
+| Typed ontology for reasoning      | ❌        | ❌ statistical graph | partial    | ✅                |
+| Keeps history / "truth at time T" | ❌        | ❌ overwrites        | partial    | ✅ *(MVP)*        |
+| Provenance + correct-from-source  | ❌        | tracking only       | partial    | ✅                |
+| Agent memory (read + write, MCP)  | ❌        | partial             | ✅         | ✅                |
+
+## Quickstart
+
+```bash
+pipx install talamus            # or: pip install talamus
+
+talamus demo                    # try a small example brain instantly (no LLM)
+talamus search "embedding"
+
+talamus init                    # your own brain (auto-detects your LLM engine)
+talamus ingest report.pdf       # PDF / DOCX / HTML / Markdown / URL -> linked concept-notes
+talamus import-vault ~/vault    # coming from Obsidian/Notion? 1:1 import, zero LLM cost
+talamus ask "how does X work?"  # cited answer
+talamus ui                      # optional web workbench (pip install talamus[ui])
+```
+
+Run `talamus` with no arguments for a status panel, or follow the
+**[10-minute quickstart](docs/quickstart.md)**.
+
+## Choose your engine
+
+Talamus runs on what you already have — set it in `talamus.json` or `TALAMUS_LLM_PROVIDER`:
+
+- `claude-cli` — your Claude subscription (default if `claude` is on PATH)
+- `codex-cli` — your ChatGPT subscription (Codex is bundled with it)
+- `gemini-cli` — your Gemini subscription
+- `opencode` — opencode, with whatever providers you configured in it
+- `antigravity-cli` — Google Antigravity (`agy`)
+- `ollama` — a local model, fully offline (`TALAMUS_LLM_MODEL=llama3`)
+- `anthropic-api` — the Anthropic API (`ANTHROPIC_API_KEY`)
+
+Every engine gets per-task **model+effort tiering** automatically: bulk work
+(extraction, routing) runs on the cheap tier, the answer you read on the strong
+one — top quality while burning as little of your subscription as possible.
+
+## For agents (MCP)
+
+```bash
+talamus mcp install             # writes .mcp.json for Claude Code / Cursor / Desktop
+talamus hook                    # prints a SessionEnd hook to auto-capture your work
+```
+
+Agents `search` / `read_note` / `recall` / `overview` / `neighbors` to read the brain,
+and `remember` to grow it. The graph is an **index, not the answer** — agents read the
+real notes and cite them.
+
+## Browse it like a wiki
+
+Open `notes/` as an Obsidian vault: notes cross-link with `[[wikilinks]]`, so you
+navigate the knowledge by hovering and clicking. Prefer a dedicated app?
+**`talamus ui`** — the local web workbench (`pip install talamus[ui]`) — gives you
+chat, search, clickable wikilinks, graph navigation, and domain browsing.
+
+## How it works
+
+Sources (Markdown, text, **PDF, DOCX, HTML, URLs**) are normalized and preserved; an
+LLM extracts atomic **concept notes** (with sources, typed relations, and wikilinks);
+Talamus builds rebuildable indexes (graph + BM25 + ontology) and a hierarchical
+**domain overview**. Retrieval routes through the overview, then **reranks** a union of
+graph + BM25 candidates, and fits the context to a **token budget** so answer cost stays
+flat as the brain grows. Answers cite the notes they used, and `talamus eval` measures
+retrieval quality (recall@k / MRR) so changes are judged by numbers, not vibes.
+
+Storage is **hybrid**: `notes/*.md` is the human-editable view (Obsidian-compatible),
+`.talamus/cache/` holds the machine truth (provenance) and the derived indexes;
+`talamus reindex` folds your hand-edits back in. The core is **Python stdlib-only**;
+extras (MCP, engines) are optional. See **[architecture](docs/architecture.md)**.
+
+## How it compares (measured)
+
+A real head-to-head against a dense vector-DB RAG pipeline (sentence-transformers
++ FAISS) and vanilla BM25, same corpus/queries/judgments
+([details](dev/research/2026-06-rs5-competitive-shootout.md)):
+
+| corpus | metric | Talamus | BM25 | Vector DB |
+|---|---|---|---|---|
+| BEIR SciFact (English, dense's turf) | recall@10 | 0.776 | 0.776 | 0.783 |
+| BEIR SciFact | hit@10 | 0.793 | 0.797 | 0.793 |
+| Cross-language + vague (our turf) | recall@10 | **0.886** | 0.771 | 0.700 |
+| Cross-language + vague | hit@10 | **0.971** | 0.829 | 0.743 |
+
+**On the vector DB's home turf we tie it — with zero embedding infrastructure.
+On cross-language and vague queries we win decisively** (the dense model lands
+last). Plus time, meaning and verifiability (100% of notes source-resolvable;
+97.7% fewer tokens than loading the brain) — moats no vector DB has.
+
+## Use cases
+
+- **Second brain** — compile your reading and notes into a connected, cited wiki.
+- **Agent memory** — give your agents a local, structured, verifiable memory they
+  can both read and grow.
+
+## Status & roadmap
+
+**Shipped** (tested, gate-green): the sources → notes → cited-answers loop;
+**multi-brain** with a federated read index (`brains`, `--all-brains`); **repo scan**
+with dry-run, secret redaction and resumable jobs (`scan`, `jobs`); **persistent
+indexes** (sqlite/FTS5 — search p95 at 10.000 notes: **34 ms**); the **Ontology Lab**
+(emergent relation types: induce → review → promote, with measured retrieval lift);
+the **temporal model** (`timeline`, `ask --as-of`); **batch verification** with a
+review queue; multi-format ingestion (PDF/DOCX/HTML/URL); the CLI dashboard; the
+**MCP server** (read+write with explicit scopes); the **UI workbench** (11 views,
+`talamus ui [--web]`).
+
+**Experimental**: emergent-schema quality at large scale (metrics built-in:
+`ontology eval`/`stability`); UI runtime polish (smoke-tested headless, verify
+rendering with `talamus ui`).
+
+**Roadmap** ([details](dev/STATE.md)): OCR &
+more formats (PPTX/XLSX/EPUB/media), packaged installers, remote
+authenticated MCP, synonym-merge for emergent types, graph canvas view.
+
+## Development
+
+```bash
+pip install -e ".[dev,mcp]"
+python dev.py                    # lint + types + tests
+```
+
+## License
+
+Apache-2.0.

talamus-1.0.0/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "talamus"
+version = "1.0.0"
+description = "Local-first knowledge compiler with graph-first retrieval for AI agents."
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "Apache-2.0" }
+authors = [
+  { name = "Talamus Contributors" }
+]
+dependencies = []
+
+[project.optional-dependencies]
+docling = ["docling>=2.0"]
+mcp = ["mcp>=1.0"]
+dev = ["ruff>=0.6", "mypy>=1.11"]
+bench = [
+    "tiktoken>=0.7",
+    "rank-bm25>=0.2",
+    "faiss-cpu>=1.8",
+    "sentence-transformers>=3.0",
+    "mem0ai>=0.1",
+]
+docs = ["mkdocs-material>=9"]
+ui = ["fastapi>=0.110", "uvicorn>=0.29", "pywebview>=5.0"]
+pdf = ["pypdf>=4"]
+
+[project.scripts]
+talamus = "talamus.cli:main"
+talamus-mcp = "talamus.mcp_server:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+talamus = ["py.typed", "webapi/static/**/*"]
+
+[tool.unittest]
+start-dir = "tests"
+
+[tool.ruff]
+target-version = "py311"
+line-length = 100
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W", "UP", "B"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["E501"]  # test data strings are legitimately long
+
+[tool.mypy]
+python_version = "3.11"
+files = ["src"]
+ignore_missing_imports = true
+check_untyped_defs = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+no_implicit_optional = true

talamus-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

talamus-1.0.0/src/talamus/__init__.py

@@ -0,0 +1,3 @@
+"""Talamus local-first knowledge compiler core."""
+
+__version__ = "0.1.0"

talamus-1.0.0/src/talamus/adapters/__init__.py

@@ -0,0 +1 @@
+"""Adattatori intercambiabili di Talamus (LLM, convertitori, ricerca, ...)."""