vismriti 0.1.0__tar.gz

vismriti-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

vismriti-0.1.0/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: vismriti
+Version: 0.1.0
+Summary: DPDP-ready consent, purpose limitation and right-to-erasure for RAG and AI agents
+Author: Malaya Kumar Swain
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/Malaya-kumar-swain/vismriti
+Project-URL: Source, https://github.com/Malaya-kumar-swain/vismriti
+Project-URL: Issues, https://github.com/Malaya-kumar-swain/vismriti/issues
+Keywords: dpdp,privacy,consent,rag,llm,ai-agents,mcp,right-to-erasure,india
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Security
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.2; extra == "mcp"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: mcp>=1.2; extra == "dev"
+Dynamic: license-file
+
+# Vismriti
+
+**Consent, purpose limitation and right-to-erasure for RAG and AI agents, built for India's DPDP Act.**
+
+*Vismriti (विस्मृति) is Sanskrit for "forgetting". Under the DPDP Act, your AI has to learn how.*
+
+[![ci](https://github.com/Malaya-kumar-swain/vismriti/actions/workflows/ci.yml/badge.svg)](https://github.com/Malaya-kumar-swain/vismriti/actions)
+![python](https://img.shields.io/badge/python-3.10%2B-blue) ![license](https://img.shields.io/badge/license-Apache--2.0-green) ![deps](https://img.shields.io/badge/core%20dependencies-0-brightgreen)
+
+---
+
+## The problem
+
+Indian companies are putting customer data into GenAI systems: support copilots, KYC assistants, sales agents. The Digital Personal Data Protection Act 2023 and the DPDP Rules 2025 now ask three questions those systems were never designed to answer:
+
+1. **Was this person's data allowed to be used for *this* purpose?** RAG retrieves whatever is semantically closest, not what the customer consented to.
+2. **When a customer withdraws consent or asks for erasure, is their data gone *everywhere*?** In an AI stack it sits in the vector index, the response cache, the agent's memory and the prompt logs.
+3. **Can you prove it?** To the customer, your DPO and the Data Protection Board.
+
+Masking Aadhaar and PAN numbers is necessary but not sufficient, and several good libraries already do it. Vismriti handles the part after masking: **consent-aware retrieval, erasure that propagates, and evidence you can hand to an auditor.**
+
+## What it does
+
+| | |
+|---|---|
+| 🧾 **Consent ledger** | Who agreed to which purpose, under which notice version, and when they withdrew. Hash-chained and tamper-evident. Retention periods lapse consent automatically. |
+| 🎯 **Purpose-bound retrieval** | A chunk reaches the model only if it was collected for the request's purpose **and every person in it** has active consent. Joint accounts and group chats included. |
+| 🧹 **Erasure that propagates** | One call withdraws consent, erases the person from the vector index, response cache, agent memory and logs, re-checks that nothing remains, and returns a **signed deletion certificate**. |
+| 🔍 **Right to access** | `access_summary()` lists purposes, consent history and items held per store, without exposing raw data. |
+| 📋 **Evidence pack** | Every allow, deny, withdrawal and erasure goes into a hash-chained log with a Markdown report mapped to DPDP sections. The log never stores raw personal data. |
+| 🇮🇳 **Indian PII masking** | Aadhaar (Verhoeff-checksum validated), PAN, GSTIN, IFSC, UPI, Indian mobile and email, including digits written in Devanagari, Odia, Bengali, Tamil, Telugu, Kannada, Gujarati and Gurmukhi. Bring your own detector through a one-method interface. |
+| 🤖 **MCP server** | Agents can call `check_purpose`, `record_consent`, `retrieve`, `access_summary` and `erase_principal` before they touch personal data. |
+
+Zero runtime dependencies in the core. The MCP server is an optional extra.
+
+## How it fits
+
+```mermaid
+flowchart LR
+    U[User / Agent request<br/>+ purpose] --> R[Purpose-bound retriever]
+    R -->|search| V[(Vector index)]
+    R -->|check each chunk| L[Consent ledger]
+    R -->|allowed chunks| M[PII masking] --> LLM[LLM]
+    R -.->|allow / deny| E[(Evidence log)]
+    X[Erase request] --> C[Erasure coordinator]
+    C --> V & K[(Response cache)] & A[(Agent memory)] & G[(App logs)]
+    C --> L
+    C --> CERT[Signed deletion certificate]
+    C -.-> E
+```
+
+## Quick start
+
+Install the library with `pip install vismriti` (or `pip install "vismriti[mcp]"` for the MCP server). To run the demo and tests, use the source:
+
+```bash
+git clone https://github.com/Malaya-kumar-swain/vismriti && cd vismriti
+pip install -e ".[dev]"
+python examples/bank_assistant_demo.py
+pytest -q
+```
+
+```python
+from vismriti import Purpose, Vismriti
+
+v = Vismriti(
+    purposes=[Purpose("kyc", "Verify identity", retention_days=3650),
+              Purpose("support", "Answer service requests", retention_days=365)],
+    signing_key=b"load-this-from-your-secret-manager",
+)
+
+v.grant("cust-asha", "support", notice_version="2026-10")
+v.ingest("ticket-1", "Asha asked to raise her UPI limit, UPI id asha.rao@okhdfcbank.",
+         principals=["cust-asha"], purposes=["support"])
+
+v.retrieve("UPI limit", purpose="support")    # → ticket-1, with the UPI id masked
+v.retrieve("UPI limit", purpose="marketing")  # → ValueError: unknown purpose (not declared)
+
+cert = v.erase("cust-asha")                   # vector index, cache, memory, logs, consents
+assert cert.complete and v.verify_certificate(cert)
+print(v.report("cust-asha"))                  # evidence pack for the DPO
+```
+
+### Demo output (abridged)
+
+```
+── 1. Support agent asks about UPI limits (purpose = support)
+  ✔ ticket-asha: Asha Rao asked to raise her UPI limit; UPI id [UPI]. Prefers Hindi.
+  ✘ ticket-ravi was withheld: Ravi never consented to 'support'.
+── 2. Marketing team tries the same data (purpose = marketing)
+  results: []  ← nothing leaks
+── 4. Asha withdraws consent and asks for erasure (DPDP s.6(4), s.12)
+  vector_index    found 2  erased 2  remaining 0
+  response_cache  found 1  erased 1  remaining 0
+  agent_memory    found 1  erased 1  remaining 0
+  app_logs        found 1  erased 1  remaining 0
+  complete=True  signature valid=True
+```
+
+## Use with AI agents (MCP)
+
+```bash
+pip install "vismriti[mcp]"
+VISMRITI_KEY=<32+ random characters> VISMRITI_PURPOSES=kyc,support python -m vismriti.mcp_server
+```
+
+Add it to any MCP client (Claude Desktop, IDE agents, your own) as a stdio server. The agent then gets tools to check purpose, record or withdraw consent, run purpose-bound retrieval, mask text, produce an access summary and erase a person.
+
+## Plug in your own stack
+
+Anything that holds personal data can join erasure by implementing two methods:
+
+```python
+class MyPgVectorStore:
+    name = "pgvector"
+    def find(self, principal_id: str) -> list[str]: ...
+    def erase(self, principal_id: str) -> int: ...
+
+v = Vismriti(purposes, key, extra_stores=[MyPgVectorStore(), MyRedisCache(), MyBackupIndex()])
+```
+
+Detectors work the same way: anything with `detect(text) -> list[Finding]` (Presidio, bharat-pii, an NER model) can replace the built-in one.
+
+## DPDP mapping
+
+See [docs/dpdp-mapping.md](https://github.com/Malaya-kumar-swain/vismriti/blob/main/docs/dpdp-mapping.md) for a section-by-section table of what is covered, what is partial and what is not yet. Limits are listed honestly in [docs/threat-model.md](https://github.com/Malaya-kumar-swain/vismriti/blob/main/docs/threat-model.md); for example, erasure covers stores, not data already baked into fine-tuned model weights.
+
+## Roadmap
+
+- [ ] Adapters: Chroma, pgvector, Qdrant, Redis, OpenSearch
+- [ ] Consent-manager integration (DPDP Rules, consent artefacts)
+- [ ] Ed25519 certificates and key rotation
+- [ ] Breach-intimation workflow (s.8(6)) and grievance tracking (s.13)
+- [ ] Right to correction (s.12) with re-embedding
+- [ ] LangChain / LlamaIndex retriever wrappers
+- [ ] Name and address detection for Indian languages via pluggable NER
+
+## Disclaimer
+
+Vismriti is an engineering aid, not legal advice. It helps you implement and evidence controls; whether a system complies with the DPDP Act depends on far more than code. All names and numbers in this repository are synthetic.
+
+## Author
+
+Built by **Malaya Kumar Swain**, AI technology leader working on agentic and voice AI, responsible AI and data platforms. · [Portfolio](https://malayakumarswain.com) · [LinkedIn](https://www.linkedin.com/in/malayakumarswain)
+
+Licensed under [Apache 2.0](https://github.com/Malaya-kumar-swain/vismriti/blob/main/LICENSE).

vismriti-0.1.0/README.md

@@ -0,0 +1,146 @@
+# Vismriti
+
+**Consent, purpose limitation and right-to-erasure for RAG and AI agents, built for India's DPDP Act.**
+
+*Vismriti (विस्मृति) is Sanskrit for "forgetting". Under the DPDP Act, your AI has to learn how.*
+
+[![ci](https://github.com/Malaya-kumar-swain/vismriti/actions/workflows/ci.yml/badge.svg)](https://github.com/Malaya-kumar-swain/vismriti/actions)
+![python](https://img.shields.io/badge/python-3.10%2B-blue) ![license](https://img.shields.io/badge/license-Apache--2.0-green) ![deps](https://img.shields.io/badge/core%20dependencies-0-brightgreen)
+
+---
+
+## The problem
+
+Indian companies are putting customer data into GenAI systems: support copilots, KYC assistants, sales agents. The Digital Personal Data Protection Act 2023 and the DPDP Rules 2025 now ask three questions those systems were never designed to answer:
+
+1. **Was this person's data allowed to be used for *this* purpose?** RAG retrieves whatever is semantically closest, not what the customer consented to.
+2. **When a customer withdraws consent or asks for erasure, is their data gone *everywhere*?** In an AI stack it sits in the vector index, the response cache, the agent's memory and the prompt logs.
+3. **Can you prove it?** To the customer, your DPO and the Data Protection Board.
+
+Masking Aadhaar and PAN numbers is necessary but not sufficient, and several good libraries already do it. Vismriti handles the part after masking: **consent-aware retrieval, erasure that propagates, and evidence you can hand to an auditor.**
+
+## What it does
+
+| | |
+|---|---|
+| 🧾 **Consent ledger** | Who agreed to which purpose, under which notice version, and when they withdrew. Hash-chained and tamper-evident. Retention periods lapse consent automatically. |
+| 🎯 **Purpose-bound retrieval** | A chunk reaches the model only if it was collected for the request's purpose **and every person in it** has active consent. Joint accounts and group chats included. |
+| 🧹 **Erasure that propagates** | One call withdraws consent, erases the person from the vector index, response cache, agent memory and logs, re-checks that nothing remains, and returns a **signed deletion certificate**. |
+| 🔍 **Right to access** | `access_summary()` lists purposes, consent history and items held per store, without exposing raw data. |
+| 📋 **Evidence pack** | Every allow, deny, withdrawal and erasure goes into a hash-chained log with a Markdown report mapped to DPDP sections. The log never stores raw personal data. |
+| 🇮🇳 **Indian PII masking** | Aadhaar (Verhoeff-checksum validated), PAN, GSTIN, IFSC, UPI, Indian mobile and email, including digits written in Devanagari, Odia, Bengali, Tamil, Telugu, Kannada, Gujarati and Gurmukhi. Bring your own detector through a one-method interface. |
+| 🤖 **MCP server** | Agents can call `check_purpose`, `record_consent`, `retrieve`, `access_summary` and `erase_principal` before they touch personal data. |
+
+Zero runtime dependencies in the core. The MCP server is an optional extra.
+
+## How it fits
+
+```mermaid
+flowchart LR
+    U[User / Agent request<br/>+ purpose] --> R[Purpose-bound retriever]
+    R -->|search| V[(Vector index)]
+    R -->|check each chunk| L[Consent ledger]
+    R -->|allowed chunks| M[PII masking] --> LLM[LLM]
+    R -.->|allow / deny| E[(Evidence log)]
+    X[Erase request] --> C[Erasure coordinator]
+    C --> V & K[(Response cache)] & A[(Agent memory)] & G[(App logs)]
+    C --> L
+    C --> CERT[Signed deletion certificate]
+    C -.-> E
+```
+
+## Quick start
+
+Install the library with `pip install vismriti` (or `pip install "vismriti[mcp]"` for the MCP server). To run the demo and tests, use the source:
+
+```bash
+git clone https://github.com/Malaya-kumar-swain/vismriti && cd vismriti
+pip install -e ".[dev]"
+python examples/bank_assistant_demo.py
+pytest -q
+```
+
+```python
+from vismriti import Purpose, Vismriti
+
+v = Vismriti(
+    purposes=[Purpose("kyc", "Verify identity", retention_days=3650),
+              Purpose("support", "Answer service requests", retention_days=365)],
+    signing_key=b"load-this-from-your-secret-manager",
+)
+
+v.grant("cust-asha", "support", notice_version="2026-10")
+v.ingest("ticket-1", "Asha asked to raise her UPI limit, UPI id asha.rao@okhdfcbank.",
+         principals=["cust-asha"], purposes=["support"])
+
+v.retrieve("UPI limit", purpose="support")    # → ticket-1, with the UPI id masked
+v.retrieve("UPI limit", purpose="marketing")  # → ValueError: unknown purpose (not declared)
+
+cert = v.erase("cust-asha")                   # vector index, cache, memory, logs, consents
+assert cert.complete and v.verify_certificate(cert)
+print(v.report("cust-asha"))                  # evidence pack for the DPO
+```
+
+### Demo output (abridged)
+
+```
+── 1. Support agent asks about UPI limits (purpose = support)
+  ✔ ticket-asha: Asha Rao asked to raise her UPI limit; UPI id [UPI]. Prefers Hindi.
+  ✘ ticket-ravi was withheld: Ravi never consented to 'support'.
+── 2. Marketing team tries the same data (purpose = marketing)
+  results: []  ← nothing leaks
+── 4. Asha withdraws consent and asks for erasure (DPDP s.6(4), s.12)
+  vector_index    found 2  erased 2  remaining 0
+  response_cache  found 1  erased 1  remaining 0
+  agent_memory    found 1  erased 1  remaining 0
+  app_logs        found 1  erased 1  remaining 0
+  complete=True  signature valid=True
+```
+
+## Use with AI agents (MCP)
+
+```bash
+pip install "vismriti[mcp]"
+VISMRITI_KEY=<32+ random characters> VISMRITI_PURPOSES=kyc,support python -m vismriti.mcp_server
+```
+
+Add it to any MCP client (Claude Desktop, IDE agents, your own) as a stdio server. The agent then gets tools to check purpose, record or withdraw consent, run purpose-bound retrieval, mask text, produce an access summary and erase a person.
+
+## Plug in your own stack
+
+Anything that holds personal data can join erasure by implementing two methods:
+
+```python
+class MyPgVectorStore:
+    name = "pgvector"
+    def find(self, principal_id: str) -> list[str]: ...
+    def erase(self, principal_id: str) -> int: ...
+
+v = Vismriti(purposes, key, extra_stores=[MyPgVectorStore(), MyRedisCache(), MyBackupIndex()])
+```
+
+Detectors work the same way: anything with `detect(text) -> list[Finding]` (Presidio, bharat-pii, an NER model) can replace the built-in one.
+
+## DPDP mapping
+
+See [docs/dpdp-mapping.md](https://github.com/Malaya-kumar-swain/vismriti/blob/main/docs/dpdp-mapping.md) for a section-by-section table of what is covered, what is partial and what is not yet. Limits are listed honestly in [docs/threat-model.md](https://github.com/Malaya-kumar-swain/vismriti/blob/main/docs/threat-model.md); for example, erasure covers stores, not data already baked into fine-tuned model weights.
+
+## Roadmap
+
+- [ ] Adapters: Chroma, pgvector, Qdrant, Redis, OpenSearch
+- [ ] Consent-manager integration (DPDP Rules, consent artefacts)
+- [ ] Ed25519 certificates and key rotation
+- [ ] Breach-intimation workflow (s.8(6)) and grievance tracking (s.13)
+- [ ] Right to correction (s.12) with re-embedding
+- [ ] LangChain / LlamaIndex retriever wrappers
+- [ ] Name and address detection for Indian languages via pluggable NER
+
+## Disclaimer
+
+Vismriti is an engineering aid, not legal advice. It helps you implement and evidence controls; whether a system complies with the DPDP Act depends on far more than code. All names and numbers in this repository are synthetic.
+
+## Author
+
+Built by **Malaya Kumar Swain**, AI technology leader working on agentic and voice AI, responsible AI and data platforms. · [Portfolio](https://malayakumarswain.com) · [LinkedIn](https://www.linkedin.com/in/malayakumarswain)
+
+Licensed under [Apache 2.0](https://github.com/Malaya-kumar-swain/vismriti/blob/main/LICENSE).

vismriti-0.1.0/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vismriti"
+version = "0.1.0"
+description = "DPDP-ready consent, purpose limitation and right-to-erasure for RAG and AI agents"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Malaya Kumar Swain" }]
+requires-python = ">=3.10"
+dependencies = []
+keywords = ["dpdp", "privacy", "consent", "rag", "llm", "ai-agents", "mcp", "right-to-erasure", "india"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Topic :: Security",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[project.optional-dependencies]
+mcp = ["mcp>=1.2"]
+dev = ["pytest>=8", "mcp>=1.2"]
+
+[project.urls]
+Homepage = "https://github.com/Malaya-kumar-swain/vismriti"
+Source = "https://github.com/Malaya-kumar-swain/vismriti"
+Issues = "https://github.com/Malaya-kumar-swain/vismriti/issues"
+
+[tool.setuptools.packages.find]
+include = ["vismriti*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

vismriti-0.1.0/setup.cfg

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

vismriti-0.1.0/tests/test_consent_and_evidence.py

@@ -0,0 +1,61 @@
+import json
+from datetime import datetime, timedelta, timezone
+
+import pytest
+
+from vismriti import ConsentLedger, EvidenceLog, Purpose
+from vismriti.consent import UnknownPurpose
+
+PURPOSES = [Purpose("kyc", "KYC"), Purpose("support", "Support", retention_days=30)]
+
+
+def test_grant_and_withdraw():
+    led = ConsentLedger(PURPOSES)
+    led.grant("p1", "kyc", "v1")
+    led.grant("p1", "support", "v1")
+    assert led.active_purposes("p1") == {"kyc", "support"}
+    led.withdraw("p1", "support")
+    assert led.active_purposes("p1") == {"kyc"}
+    led.grant("p1", "support", "v2")  # re-consent under a new notice
+    assert led.is_permitted("p1", "support")
+
+
+def test_withdraw_all():
+    led = ConsentLedger(PURPOSES)
+    led.grant("p1", "kyc", "v1")
+    led.grant("p1", "support", "v1")
+    assert sorted(r["purpose"] for r in led.withdraw("p1")) == ["kyc", "support"]
+    assert led.active_purposes("p1") == set()
+
+
+def test_unknown_purpose_rejected():
+    with pytest.raises(UnknownPurpose):
+        ConsentLedger(PURPOSES).grant("p1", "marketing", "v1")
+
+
+def test_retention_lapses_consent():
+    led = ConsentLedger(PURPOSES)
+    led.grant("p1", "support", "v1")
+    later = datetime.now(timezone.utc) + timedelta(days=31)
+    assert "support" not in led.active_purposes("p1", at=later)
+
+
+def test_ledger_tamper_detected(tmp_path):
+    path = tmp_path / "consent.jsonl"
+    led = ConsentLedger(PURPOSES, path)
+    led.grant("p1", "kyc", "v1")
+    led.withdraw("p1", "kyc")
+    assert ConsentLedger(PURPOSES, path).verify()
+    lines = path.read_text().splitlines()
+    rec = json.loads(lines[1])
+    rec["type"] = "grant"  # someone tries to undo the withdrawal
+    lines[1] = json.dumps(rec)
+    path.write_text("\n".join(lines) + "\n")
+    assert not ConsentLedger(PURPOSES, path).verify()
+
+
+def test_evidence_report_has_no_raw_text():
+    ev = EvidenceLog()
+    ev.record("retrieval_denied", principals=["p1"], purpose="marketing", chunk="c1", reason="no consent")
+    report = ev.report("p1")
+    assert "retrieval_denied" in report and "verified" in report

vismriti-0.1.0/tests/test_mcp_server.py

@@ -0,0 +1,21 @@
+import asyncio
+
+import pytest
+
+pytest.importorskip("mcp")
+
+from vismriti import Purpose, Vismriti  # noqa: E402
+from vismriti.mcp_server import build  # noqa: E402
+
+
+def test_tools_registered_and_callable():
+    v = Vismriti([Purpose("kyc", "KYC")], b"test-key-0123456789abcdef")
+    server = build(v)
+    names = {t.name for t in asyncio.run(server.list_tools())}
+    assert {"check_purpose", "record_consent", "withdraw_consent", "retrieve",
+            "mask_text", "access_summary", "erase_principal"} <= names
+
+    asyncio.run(server.call_tool("record_consent", {"principal_id": "p1", "purpose": "kyc"}))
+    assert v.ledger.is_permitted("p1", "kyc")
+    asyncio.run(server.call_tool("erase_principal", {"principal_id": "p1"}))
+    assert not v.ledger.is_permitted("p1", "kyc")