Semantische Suche in deinen Telegram-Memes. Frag auf Russisch oder Englisch — finde das Meme, an das du dich nur halb erinnerst.
Pipeline: Telegram-Export → Vision-Bildunterschriften (zweisprachig) + OCR → mehrsprachige Embeddings (bge-m3, lokal) → PostgreSQL/pgvector-Hybridsuche (dense + Volltext, RRF) → Cross-Encoder-Reranking. Verfügbar als CLI, Web-UI und MCP-Server, damit dein KI-Assistent auch deine Memes durchsuchen kann.
Siehe die Design-Spezifikation für die vollständige Architektur.
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 APIDer Telegram-Export wird in data/ gespeichert (Telegram Desktop → Chatverlauf exportieren → Fotos, JSON-Format). Memes und exportierte Daten bleiben lokal — data/ ist von Git ignoriert; nur Code wird veröffentlicht.
Related MCP server: local-docs-mcp
Gemessen an einem Golden Set aus 21 Abfragen, das über den UI-Feedback-Button ("это он ✓") gesammelt wurde, sowie einem Pilot-Korpus von 400 Bildern. Jede Retrieval-Ebene wurde erst hinzugefügt, nachdem sie sich bewährt hatte:
Ebene | hit@5 | hit@10 | MRR |
nur Dense-Vektoren | 0.857 | 0.905 | 0.768 |
+ Volltextsuche, RRF-Fusion | 0.905 | 0.952 | 0.815 |
+ Cross-Encoder-Reranker | 0.905 | 1.000 | 0.839 |
Der Vergleich der Captioning-Modelle anhand desselben Korpus und Golden Set: qwen3-vl-8b erreichte oder übertraf qwen3-vl-235b bei den Retrieval-Metriken zu einem Drittel des Preises, daher wird der gesamte Korpus mit dem 8b-Modell indexiert (~$3.6 für ~11k Bilder). Ein in der Evals-Historie dokumentierter Vorbehalt: Das Golden Set wurde auf Basis des 8b-Index gesammelt, was den Vergleich zugunsten des 8b-Modells verzerrt.
Die Suchkonfiguration wird über Umgebungsvariablen gesteuert: MEMGREP_SEARCH_MODE=vector|hybrid, MEMGREP_RERANK_ENABLED=true|false. memgrep evals schreibt pro Konfiguration ein JSON mit Zeitstempel in evals/results/, sodass Läufe vergleichbar bleiben.
Lass Claude (oder einen beliebigen MCP-Client) deine Memes durchsuchen:
claude mcp add memgrep -- uv run --directory /absolute/path/to/memgrep python -m memgrep.mcp_serverTools: search_memes(query, k) gibt Treffer mit Dateipfaden und Bildunterschriften zurück; get_meme(sha256) gibt das Bild selbst zurück.
Der Befehl memgrep watch verfolgt einen Telegram-Kanal in Echtzeit per Bot-API-Long-Polling. Richte den Bot als Kanaladministrator ein, konfiguriere MEMGREP_TG_BOT_TOKEN und MEMGREP_TG_CHANNEL_ID und starte den Watcher-Dienst. Neue Fotos, die im Kanal gepostet werden, werden automatisch indexiert: sie erhalten Bildunterschriften, werden eingebettet und sind innerhalb von Minuten durchsuchbar. Reaktionen auf aktuelle Beiträge werden ebenfalls zurück in die Datenbank synchronisiert, um das Engagement zu verfolgen.
Python 3.12+, uv, PostgreSQL 17 + pgvector, sentence-transformers (BAAI/bge-m3-Embeddings, BAAI/bge-reranker-v2-m3-Reranker, beide lokal), ein beliebiger OpenAI-kompatibler Vision-Endpunkt zum Erstellen von Bildunterschriften (Standard: OpenRouter, qwen3-vl), FastAPI, typer, MCP Python SDK. 49 Tests, keine Netzwerk- oder Modell-Downloads in der Testsuite.
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
