MLOps / AI 工程

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

聚合55+平台热门榜单数据的AI工具，支持微博、知乎、B站、GitHub等平台。适用于LLM/RAG场景。

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.

Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.

Orchestrate end-to-end machine learning pipelines using Prefect or Airflow with DAG construction, task dependencies, retry logic, scheduling, monitoring, and integration with MLflow, DVC, and feature stores for production ML workflows. Use when automating multi-step ML workflows from data ingestion…

Together AI ci integration for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together ci integration".

Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG.

Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 43 tools, no cloud.

Read-only, zero-key MCP server for point-in-time AI model API prices. Open data, CC BY 4.0.

Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, quotes, gov map, RAG.

Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 49 tools, no cloud.

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth

Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.

Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.

Inject, parse, and strip [N] citation markers in RAG outputs.

MCP server for rag knowledge. Features semantic search, knowledge graph query, index documen...

A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-eng…

Review multi-tenant AI deployments for cross-tenant context leakage, LoRA adapter contamination, shared inference worker risks, system prompt bleed, and tenant isolation failures in model serving infrastructure.

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes ~500-1500 tokens per delegation regardless of how many file reads…

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Ja…

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for h…

SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

OpenAI-compatible AI inference, code, embeddings & agent tools for bots — and mine ANM.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.