What document types can it index and search?

It supports over 40 types including Markdown, CSV, XLSX, PDF, code files, and images.

How is search implemented?

Search combines vector similarity via LanceDB with keyword BM25 scoring, then reranks results with weighted semantic and keyword scores.

Is data encrypted at rest?

Yes, if you set the TESSERA_VAULT_KEY environment variable, all stored memories are encrypted using AES-256-CBC.

How do I install and set up this server?

Install with 'pip install project-tessera' and run 'tessera setup' to initialize the local memory for Claude Desktop.

Project Tessera

Q: Does this server require API keys or internet access?

No, it runs fully locally without any API keys or external service dependencies.

knowledge-basememoryvector-searchlocalencryption

Local knowledge base with encrypted vector search, multi-format document indexing, and cross-session memory for Claude Desktop.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

We couldn’t automatically confirm this listing starts correctly

The install command below didn't complete successfully in our automated test.

uvx --from

error: a value is required for '--from <FROM>' but none was supplied For more information, try '--help'.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "besslframework-stack-project-tessera": {
      "command": "uvx",
      "args": [
        "--from"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

This server provides persistent local memory and document search for Claude Desktop without requiring API keys or Docker. It indexes over 40 document types into a vector store with hybrid semantic and keyword search, contradiction detection, confidence scoring, and auto-learning from conversations. The system runs fully locally using embedded LanceDB and fastembed, supports AES-256-CBC encryption, and exposes a comprehensive HTTP API for automation and integration.

Use cases

Persist AI session memory across conversations

Index and search diverse document formats locally

Detect contradictions and score memory confidence

Automate knowledge base access via HTTP API

Visualize knowledge graphs from stored memories

Key features

Hybrid vector and keyword search with reranking

Supports 40+ document types including Markdown, CSV, PDF, code

Self-maintaining memory with contradiction detection and auto-merge

AES-256-CBC encrypted vault for data at rest

58 REST API endpoints for integration and automation

Zero external dependencies; no Docker or API keys required

Capabilities & Tool Schemas (53)Self-reported

Inspect callable tools, capabilities, and parameters exposed to AI agents by Project Tessera.

search_documents

Semantic + keyword hybrid search across all docs

unified_search

Search documents AND memories in one call

view_file_full

Full file view (CSV as table, XLSX per sheet)

read_file

Read any file's full content

list_sources

See what's indexed

remember

Save knowledge that persists across sessions

Documentation Overview

Tessera

Every AI conversation produces knowledge. When the session ends, it's gone. Tessera keeps it.

One knowledge base for Claude Desktop, with an HTTP API for scripts and automation. Runs locally. No API keys, no Docker, no data leaving your machine.

Terminal

pip install project-tessera
tessera setup
# Done. Claude Desktop now has persistent memory + document search.

Why Tessera over alternatives

	Tessera	Mem0	Basic Memory	mcp-memory-service
Works without API keys	Yes	No (needs OpenAI)	Yes	Partial
Works without Docker	Yes	No	Yes	No
Document search (40+ types)	Yes	No	Markdown only	No
ChatGPT integration (via tunnel)	Yes	No	No	No
Contradiction detection	Yes	No	No	No
Memory confidence scoring	Yes	No	No	No
Encrypted vault (AES-256)	Yes	No	No	No
HTTP API for non-MCP tools	58 endpoints	Yes	No	Yes
Auto-learning from conversations	Yes	Yes	No	No
MCP tools	58	~10	~15	24

The short version

Most memory tools store text and search it. Tessera does that, plus:

HTTP API: 58 REST endpoints let scripts, ChatGPT (via tunnel + Custom GPT Actions), and local LLMs read and write the same knowledge base.
Self-maintaining: finds contradictions between old and new memories, scores confidence by reinforcement frequency, flags stale knowledge, auto-merges near-duplicates.
Zero infrastructure: pip install and go. LanceDB and fastembed are embedded -- no Docker, no database server, no API keys.
Encrypted: set TESSERA_VAULT_KEY and all memories are AES-256-CBC encrypted at rest.

Architecture

How search works (query path)

Code

    User asks: "What did we decide about the database?"
                            |
                            v
                +-----------------------+
                |    Query Processing   |
                |  Multi-angle decomp   |    "database decision"
                |  (2-4 perspectives)   |    "database", "decision"
                +-----------------------+    "decision about database"
                            |
              +-------------+-------------+
              |                           |
              v                           v
    +------------------+        +------------------+
    |  Vector Search   |        |  Keyword Search  |
    |  (LanceDB)       |        |  (FTS index)     |
    |  384-dim MiniLM  |        |  BM25 scoring    |
    +------------------+        +------------------+
              |                           |
              +-------------+-------------+
                            |
                            v
                +-----------------------+
                |      Reranking        |
                |  70% semantic weight  |    LinearCombinationReranker
                |  30% keyword weight   |    + version-aware scoring
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Result Assembly     |
                |  Dedup (content hash) |    2-pass deduplication
                |  Verdict labels       |    found / weak / none
                |  Cache (60s TTL)      |
                +-----------------------+
                            |
                            v
                    Top-K results with
                    confidence scores

How ingestion works (ingest path)

Code

    Documents: .md .pdf .docx .xlsx .py .ts .go ...  (40+ types)
                            |
                            v
                +-----------------------+
                |   File Type Router    |
                |  Markdown, CSV, XLSX  |    Type-specific parsers
                |  Code, PDF, Images    |    with metadata extraction
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Chunking Engine     |
                |  1024 tokens/chunk    |    Sentence-boundary aware
                |  100 token overlap    |    Heading-preserving
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Local Embedding     |
                |  fastembed/ONNX       |    paraphrase-multilingual
                |  384 dimensions       |    MiniLM-L12-v2
                |  No API calls         |    101 languages
                +-----------------------+
                            |
              +-------------+-------------+
              |                           |
              v                           v
    +------------------+        +------------------+
    |    LanceDB       |        |     SQLite       |
    |  Vector storage  |        |  File metadata   |
    |  Columnar format |        |  Search analytics|
    |  Zero-config     |        |  Interaction log |
    +------------------+        +------------------+

System overview

Code

                    +--------------------------------------------+
                    |              src/core.py                    |
                    |         58 orchestration functions          |
                    |   69 specialized modules, 31k LOC           |
                    +--------------------------------------------+
                     /                |                \
    +---------------+  +-------------------+  +--------------+
    | MCP Server    |  | HTTP API Server   |  | CLI          |
    | Claude Desktop|  | FastAPI + Swagger |  | 11 commands  |
    | 58 tools      |  | 58 endpoints      |  | setup, sync  |
    | stdio         |  | port 8394         |  | ingest, api  |
    +---------------+  +-------------------+  +--------------+
           |                    |                     |
           v                    v                     v
    +------------------------------------------------------------+
    |                    Storage Layer                            |
    |  LanceDB         SQLite           Filesystem               |
    |  (vectors)       (metadata,       (memories as .md,        |
    |                   analytics,       encrypted with           |
    |                   interactions)    AES-256-CBC)             |
    |                                                            |
    |  fastembed/ONNX: local embedding, no API keys              |
    |  101 languages, 384-dim vectors, ~220MB model              |
    +------------------------------------------------------------+

Get started

1. Install

Terminal

pip install project-tessera

Or with uv:

bash

uvx --from project-tessera tessera setup

2. Setup

bash

tessera setup

Creates workspace config, downloads embedding model (~220MB, first time only), configures Claude Desktop.

3. Restart Claude Desktop

Ask Claude about your documents. It searches automatically.

Use with ChatGPT (Custom GPT Actions)

bash

tessera api                     # Start REST API on localhost:8394
ngrok http 8394                 # Expose to the internet
# Then create a Custom GPT with the Actions spec from /chatgpt-actions/openapi.json

Full setup guide at http://127.0.0.1:8394/chatgpt-actions/setup. Swagger docs at http://127.0.0.1:8394/docs.

How it works

Hybrid search with reranking

Every search goes through four stages:

Query decomposition -- the query is split into 2-4 search angles (core keywords, individual terms, reversed emphasis)
Hybrid retrieval -- vector similarity (LanceDB) and keyword matching (FTS/BM25) run in parallel
Reranking -- a LinearCombinationReranker merges the two result sets (70% semantic, 30% keyword weight)
Verdict scoring -- each result gets a label: confident match (>= 45%), possible match (25-45%), or low relevance (< 25%)

When multiple versions of the same document exist, Tessera prefers the latest.

Cross-session memory

bash

# Via MCP (Claude)
"Remember that we chose PostgreSQL for the production database"

# Via HTTP API (scripts, local LLMs, ChatGPT via tunnel)
curl -X POST http://127.0.0.1:8394/remember \
  -H "Content-Type: application/json" \
  -d '{"content": "Use PostgreSQL for production", "tags": ["db", "architecture"]}'

Each memory gets a category (decision, preference, or fact), is checked for duplicates against existing memories (cosine similarity, 0.92 threshold), and receives a confidence score -- weighted by repetition (35%), recency (25%), source diversity (20%), and category (20%). Set TESSERA_VAULT_KEY to encrypt all memories with AES-256-CBC.

Auto-learning

Tessera picks up decisions, preferences, and facts from your conversations without being asked. toggle_auto_learn turns it on or off; review_learned shows what it caught.

Contradiction detection

Memories contradict each other over time. Tessera finds them:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5mo ago

Most recent push to the default branch.

Install check

Inconclusive

Install command did not finish in our automated test.

Tools exposed

Callable tools this server registers over MCP.

Directory activity

2 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Project Tessera

No, it runs fully locally without any API keys or external service dependencies.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/besslframework-stack-project-tessera?style=directory)](https://allmcps.com/mcp/besslframework-stack-project-tessera)

HTML Embed

<a href="https://allmcps.com/mcp/besslframework-stack-project-tessera"><img src="https://allmcps.com/api/badge/besslframework-stack-project-tessera?style=directory" alt="Project Tessera on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

PricingFree

56Quality signal: Good · 56/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools29/30

Adoption & activity3/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 23d ago via OSV.dev · --from (PyPI)

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Project Tessera →Install in Claude Desktop Install in Cursor Install in VS Code

Project Tessera

knowledge-basememoryvector-searchlocalencryption

Local knowledge base with encrypted vector search, multi-format document indexing, and cross-session memory for Claude Desktop.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

We couldn’t automatically confirm this listing starts correctly

The install command below didn't complete successfully in our automated test.

uvx --from

error: a value is required for '--from <FROM>' but none was supplied For more information, try '--help'.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "besslframework-stack-project-tessera": {
      "command": "uvx",
      "args": [
        "--from"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

Use cases

Persist AI session memory across conversations

Index and search diverse document formats locally

Detect contradictions and score memory confidence

Automate knowledge base access via HTTP API

Visualize knowledge graphs from stored memories

Key features

Hybrid vector and keyword search with reranking

Supports 40+ document types including Markdown, CSV, PDF, code

Self-maintaining memory with contradiction detection and auto-merge

AES-256-CBC encrypted vault for data at rest

58 REST API endpoints for integration and automation

Zero external dependencies; no Docker or API keys required

Capabilities & Tool Schemas (53)Self-reported

Inspect callable tools, capabilities, and parameters exposed to AI agents by Project Tessera.

search_documents

Semantic + keyword hybrid search across all docs

unified_search

Search documents AND memories in one call

view_file_full

Full file view (CSV as table, XLSX per sheet)

read_file

Read any file's full content

list_sources

See what's indexed

remember

Save knowledge that persists across sessions

Documentation Overview

Tessera

Every AI conversation produces knowledge. When the session ends, it's gone. Tessera keeps it.

One knowledge base for Claude Desktop, with an HTTP API for scripts and automation. Runs locally. No API keys, no Docker, no data leaving your machine.

Terminal

pip install project-tessera
tessera setup
# Done. Claude Desktop now has persistent memory + document search.

Why Tessera over alternatives

	Tessera	Mem0	Basic Memory	mcp-memory-service
Works without API keys	Yes	No (needs OpenAI)	Yes	Partial
Works without Docker	Yes	No	Yes	No
Document search (40+ types)	Yes	No	Markdown only	No
ChatGPT integration (via tunnel)	Yes	No	No	No
Contradiction detection	Yes	No	No	No
Memory confidence scoring	Yes	No	No	No
Encrypted vault (AES-256)	Yes	No	No	No
HTTP API for non-MCP tools	58 endpoints	Yes	No	Yes
Auto-learning from conversations	Yes	Yes	No	No
MCP tools	58	~10	~15	24

The short version

Most memory tools store text and search it. Tessera does that, plus:

HTTP API: 58 REST endpoints let scripts, ChatGPT (via tunnel + Custom GPT Actions), and local LLMs read and write the same knowledge base.
Self-maintaining: finds contradictions between old and new memories, scores confidence by reinforcement frequency, flags stale knowledge, auto-merges near-duplicates.
Zero infrastructure: pip install and go. LanceDB and fastembed are embedded -- no Docker, no database server, no API keys.
Encrypted: set TESSERA_VAULT_KEY and all memories are AES-256-CBC encrypted at rest.

Architecture

How search works (query path)

Code

    User asks: "What did we decide about the database?"
                            |
                            v
                +-----------------------+
                |    Query Processing   |
                |  Multi-angle decomp   |    "database decision"
                |  (2-4 perspectives)   |    "database", "decision"
                +-----------------------+    "decision about database"
                            |
              +-------------+-------------+
              |                           |
              v                           v
    +------------------+        +------------------+
    |  Vector Search   |        |  Keyword Search  |
    |  (LanceDB)       |        |  (FTS index)     |
    |  384-dim MiniLM  |        |  BM25 scoring    |
    +------------------+        +------------------+
              |                           |
              +-------------+-------------+
                            |
                            v
                +-----------------------+
                |      Reranking        |
                |  70% semantic weight  |    LinearCombinationReranker
                |  30% keyword weight   |    + version-aware scoring
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Result Assembly     |
                |  Dedup (content hash) |    2-pass deduplication
                |  Verdict labels       |    found / weak / none
                |  Cache (60s TTL)      |
                +-----------------------+
                            |
                            v
                    Top-K results with
                    confidence scores

How ingestion works (ingest path)

Code

    Documents: .md .pdf .docx .xlsx .py .ts .go ...  (40+ types)
                            |
                            v
                +-----------------------+
                |   File Type Router    |
                |  Markdown, CSV, XLSX  |    Type-specific parsers
                |  Code, PDF, Images    |    with metadata extraction
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Chunking Engine     |
                |  1024 tokens/chunk    |    Sentence-boundary aware
                |  100 token overlap    |    Heading-preserving
                +-----------------------+
                            |
                            v
                +-----------------------+
                |   Local Embedding     |
                |  fastembed/ONNX       |    paraphrase-multilingual
                |  384 dimensions       |    MiniLM-L12-v2
                |  No API calls         |    101 languages
                +-----------------------+
                            |
              +-------------+-------------+
              |                           |
              v                           v
    +------------------+        +------------------+
    |    LanceDB       |        |     SQLite       |
    |  Vector storage  |        |  File metadata   |
    |  Columnar format |        |  Search analytics|
    |  Zero-config     |        |  Interaction log |
    +------------------+        +------------------+

System overview

Code

                    +--------------------------------------------+
                    |              src/core.py                    |
                    |         58 orchestration functions          |
                    |   69 specialized modules, 31k LOC           |
                    +--------------------------------------------+
                     /                |                \
    +---------------+  +-------------------+  +--------------+
    | MCP Server    |  | HTTP API Server   |  | CLI          |
    | Claude Desktop|  | FastAPI + Swagger |  | 11 commands  |
    | 58 tools      |  | 58 endpoints      |  | setup, sync  |
    | stdio         |  | port 8394         |  | ingest, api  |
    +---------------+  +-------------------+  +--------------+
           |                    |                     |
           v                    v                     v
    +------------------------------------------------------------+
    |                    Storage Layer                            |
    |  LanceDB         SQLite           Filesystem               |
    |  (vectors)       (metadata,       (memories as .md,        |
    |                   analytics,       encrypted with           |
    |                   interactions)    AES-256-CBC)             |
    |                                                            |
    |  fastembed/ONNX: local embedding, no API keys              |
    |  101 languages, 384-dim vectors, ~220MB model              |
    +------------------------------------------------------------+

Get started

1. Install

Terminal

pip install project-tessera

Or with uv:

bash

uvx --from project-tessera tessera setup

2. Setup

bash

tessera setup

Creates workspace config, downloads embedding model (~220MB, first time only), configures Claude Desktop.

3. Restart Claude Desktop

Ask Claude about your documents. It searches automatically.

Use with ChatGPT (Custom GPT Actions)

bash

tessera api                     # Start REST API on localhost:8394
ngrok http 8394                 # Expose to the internet
# Then create a Custom GPT with the Actions spec from /chatgpt-actions/openapi.json

Full setup guide at http://127.0.0.1:8394/chatgpt-actions/setup. Swagger docs at http://127.0.0.1:8394/docs.

How it works

Hybrid search with reranking

Every search goes through four stages:

Query decomposition -- the query is split into 2-4 search angles (core keywords, individual terms, reversed emphasis)
Hybrid retrieval -- vector similarity (LanceDB) and keyword matching (FTS/BM25) run in parallel
Reranking -- a LinearCombinationReranker merges the two result sets (70% semantic, 30% keyword weight)
Verdict scoring -- each result gets a label: confident match (>= 45%), possible match (25-45%), or low relevance (< 25%)

When multiple versions of the same document exist, Tessera prefers the latest.

Cross-session memory

bash

# Via MCP (Claude)
"Remember that we chose PostgreSQL for the production database"

# Via HTTP API (scripts, local LLMs, ChatGPT via tunnel)
curl -X POST http://127.0.0.1:8394/remember \
  -H "Content-Type: application/json" \
  -d '{"content": "Use PostgreSQL for production", "tags": ["db", "architecture"]}'

Auto-learning

Tessera picks up decisions, preferences, and facts from your conversations without being asked. toggle_auto_learn turns it on or off; review_learned shows what it caught.

Contradiction detection

Memories contradict each other over time. Tessera finds them:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5mo ago

Most recent push to the default branch.

Install check

Inconclusive

Install command did not finish in our automated test.

Tools exposed

Callable tools this server registers over MCP.

Directory activity

2 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Project Tessera

No, it runs fully locally without any API keys or external service dependencies.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/besslframework-stack-project-tessera?style=directory)](https://allmcps.com/mcp/besslframework-stack-project-tessera)

HTML Embed

<a href="https://allmcps.com/mcp/besslframework-stack-project-tessera"><img src="https://allmcps.com/api/badge/besslframework-stack-project-tessera?style=directory" alt="Project Tessera on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

PricingFree

56Quality signal: Good · 56/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools29/30

Adoption & activity3/15

Community engagement0/10

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 23d ago via OSV.dev · --from (PyPI)

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Project Tessera →Install in Claude Desktop Install in Cursor Install in VS Code