Búsqueda semántica en tus memes de Telegram. Pregunta en ruso o inglés — encuentra el meme que recuerdas a medias.
Flujo: exportación de Telegram → descripciones por visión (bilingües) + OCR → embeddings multilingües (bge-m3, local) → búsqueda híbrida PostgreSQL/pgvector (densa + texto completo, RRF) → reordenamiento con cross-encoder. Se expone como CLI, interfaz web y servidor MCP, para que tu asistente de IA también pueda buscar tus memes.
Consulta la especificación de diseño para ver la arquitectura completa.
cp .env.example .env # fill in OpenRouter API key
make up # PostgreSQL + pgvector on :5433
make test
uv run memgrep ingest # load data/result.json + photos into the db
uv run memgrep caption --limit 400 # describe images via a vision model (pilot)
uv run memgrep embed # local bge-m3 embeddings
uv run memgrep search "this is fine" # CLI search; --open shows files in Preview
uv run memgrep serve # web UI on localhost:8000
uv run memgrep evals # golden-set metrics for the current config
uv run memgrep sync # ingest + caption + embed for new exports
uv run memgrep watch # follow the channel via Bot APILa exportación de Telegram se guarda en data/ (Telegram Desktop → Exportar historial de chat → Fotos, formato JSON). Los memes y los datos exportados permanecen en local — data/ está ignorado por git; solo se publica el código.
Related MCP server: local-docs-mcp
Medido en un conjunto de referencia de 21 consultas recopilado mediante el botón de comentarios de la interfaz ("это он ✓"), con un corpus piloto de 400 imágenes. Cada capa de recuperación se añadió solo tras demostrar su eficacia:
Capa | hit@5 | hit@10 | MRR |
solo vectores densos | 0.857 | 0.905 | 0.768 |
+ búsqueda de texto completo, fusión RRF | 0.905 | 0.952 | 0.815 |
+ reordenador cross-encoder | 0.905 | 1.000 | 0.839 |
Comparación de modelos de descripción en el mismo corpus y conjunto de referencia: qwen3-vl-8b igualó o superó a qwen3-vl-235b en métricas de recuperación a un tercio del precio, por lo que todo el corpus está indexado con el modelo de 8b (~$3.6 por ~11k imágenes). Advertencia documentada en el historial de evaluaciones: el conjunto de referencia se recopiló sobre el índice de 8b, lo que sesga la comparación a su favor.
La configuración de búsqueda se controla mediante variables de entorno: MEMGREP_SEARCH_MODE=vector|hybrid, MEMGREP_RERANK_ENABLED=true|false. memgrep evals escribe un JSON con marca de tiempo por configuración en evals/results/ para que las ejecuciones sigan siendo comparables.
Permite que Claude (o cualquier cliente MCP) busque en tus memes:
claude mcp add memgrep -- uv run --directory /absolute/path/to/memgrep python -m memgrep.mcp_serverHerramientas: search_memes(query, k) devuelve coincidencias con rutas de archivo y descripciones; get_meme(sha256) devuelve la imagen en sí.
El comando memgrep watch sigue un canal de Telegram en tiempo real mediante long polling de la Bot API. Configura el bot como administrador del canal, define MEMGREP_TG_BOT_TOKEN y MEMGREP_TG_CHANNEL_ID, y ejecuta el servicio de monitorización. Las fotos nuevas que se publiquen en el canal se indexan automáticamente: reciben una descripción, se convierten en embeddings y se pueden buscar en minutos. Las reacciones a las publicaciones recientes también se sincronizan de vuelta con la base de datos para realizar un seguimiento de la interacción.
Python 3.12+, uv, PostgreSQL 17 + pgvector, sentence-transformers (embeddings BAAI/bge-m3, reranker BAAI/bge-reranker-v2-m3, ambos locales), cualquier endpoint de visión compatible con OpenAI para generar descripciones (por defecto: OpenRouter, qwen3-vl), FastAPI, typer, MCP Python SDK. 49 pruebas, sin descargas de red ni de modelos en la suite de pruebas.
Return the meme image itself by sha256 from a search_memes result.
| Name | Required | Description | Default |
|---|---|---|---|
| sha256 | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure burden. It states the core behavior (returning the image binary for a given hash) and implies a read-only action, but it does not disclose output format (e.g., binary, base64), error conditions, or whether any authentication is required. This is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler words. Every phrase contributes meaning: 'meme image itself' clarifies the return value, 'by sha256' identifies the key parameter, and 'from a search_memes result' indicates the source workflow.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and no output schema, the description is largely complete: it identifies the input provenance, the operation, and the result. It does not mention potential errors or the exact binary format, but given the tool's simplicity the missing details are minor and unlikely to cause incorrect invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides only the parameter name and type (string) with 0% description coverage, so the description must add meaning. It does this by explaining that the sha256 parameter comes from a search_memes result, giving the agent crucial context on how to obtain a valid value. It could specify the expected format (e.g., hex-encoded SHA-256), but the guidance is already helpful.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Return') and names a precise resource ('the meme image itself') with a clear retrieval mechanism ('by sha256'). Referencing 'from a search_memes result' distinguishes it from its sibling tool search_memes, which presumably returns metadata or search results rather than the image content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies the intended usage: call this tool with a sha256 obtained from search_memes to fetch the actual image. It doesn't explicitly state exclusions or when to prefer alternatives, but for a simple single-purpose tool the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Semantic search over the meme collection. Query in Russian or English.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | ||
| query | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden; it does convey that matching is semantic rather than exact and that the query language is flexible. It does not state read-only behavior, result ordering, or limitations, but for a simple search tool the disclosed traits are non-trivial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences carry the essential message, with the main action stated first and no filler. Every phrase earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter search with an output schema, the description is nearly sufficient, but it leaves two gaps: the meaning/behavior of 'k' and the relationship to the sibling get_meme tool. This is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It adds meaning to 'query' by explaining the search is semantic and accepts Russian or English, but it remains silent on the 'k' parameter. The compensation is partial, making this minimum viable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb and resource ('Semantic search over the meme collection') and the 'semantic' qualifier distinguishes it from a direct fetch like get_meme. It is clear, but it does not explicitly name or contrast the sibling tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'Semantic search over the meme collection' implies when the tool is relevant, and 'Query in Russian or English' gives practical input guidance. However, it offers no explicit direction on when to choose this over get_meme or what types of queries are not appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: one performs semantic search over the collection, the other retrieves a specific image by hash. There is no overlap or ambiguity between them.
Both tools follow the same verb_noun pattern in snake_case: search_memes and get_meme. The singular/plural variation is natural for resource action and does not break consistency.
With only two tools, the server feels thin and sits at the low end of the borderline range. However, the narrow purpose of search and retrieval justifies a minimal surface, so it is not unreasonable.
For a read-only meme search and retrieval server, the surface is complete: search returns hashes and get_meme fetches the image. There are no dead ends or missing core operations within this defined scope.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Memory system for AI agents with semantic search. Store and recall memories with ease.
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Persistent AI memory with semantic search, conflict detection, and ticketing.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Milflopper/memgrep'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
