llm-ai
26
cache-cost-tracking
LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.
yonatangross
data-ai
sorting
์คํ
current ordering strategy
query
all entries
refine the visible subset
llm-ai
26
mem0-memory
Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.
yonatangross
data-ai
llm-ai
26
langgraph-parallel
LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.
yonatangross
data-ai
llm-ai
26
pgvector-search
Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.
yonatangross
data-ai
llm-ai
26
function-calling
LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.
yonatangross
data-ai
llm-ai
26
load-context
Auto-load relevant memories at session start from both mem0 and graph
yonatangross
data-ai
llm-ai
26
ai-proofreading
็ณป็ปๅ้ไฝAIๆฃๆต็่ณ30%ไปฅไธ๏ผ้่ฟไธ้ๅฎกๆ กๆต็จ๏ผๅ ๅฎนใ้ฃๆ ผใ็ป่๏ผๅขๅ ไบบๅณใๅฝ็จๆทๆๅฐ"AIๅณๅคช้"ใ"ๅAIๅ็"ใ"้ไฝAIๆฃๆต็"ใ"ๆดๅไบบๅ็"ใ"่ช็ถไธไบ"ใ"ๅฃ่ฏญๅ"ๆถไฝฟ็จๆญคๆ่ฝใ
alchaincyf
data-ai
llm-ai
26
add-golden
Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.
yonatangross
data-ai
llm-ai
26
post-game-press-conference-simulator
Generate realistic coach/player interview responses for wins, losses, controversies, injuries. Authentic coachspeak and player personalities.
OneWave-AI
data-ai
llm-ai
26
prompt-caching
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
yonatangross
data-ai
llm-ai
26
context-compression
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
yonatangross
data-ai
llm-ai
26
langfuse-observability
LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.
yonatangross
data-ai
llm-ai
26
prompt-classifier
่ชๅจ่ฏๅซprompt็ฑปๅๅนถไฟๅญๅฐ็ธๅบๅ็ฑป๏ผๆๆฏ/ๅ ๅฎน/ๆๅญฆ/ไบงๅ/้็จ๏ผ๏ผๆฏๆ่ชๅจๆไปถๅฝๅๅ็ดขๅผ็ฎก็ใๅฝ็จๆทๆๅฐ"ไฟๅญprompt"ใ"่ฎฐๅฝprompt"ใ"็ฎก็prompt"ใ"ๆด็prompt"ใ"promptๅบ"ๆถไฝฟ็จๆญคๆ่ฝใ
alchaincyf
data-ai
llm-ai
26
langgraph-supervisor
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
yonatangross
data-ai
llm-ai
26
llm-streaming
LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.
yonatangross
data-ai
llm-ai
26
defense-in-depth
Use when building secure AI pipelines or hardening LLM integrations. Implements 8 validation layers from edge to storage with no single point of failure.
yonatangross
data-ai
llm-ai
26
langgraph-functional
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
yonatangross
data-ai
llm-ai
26
contextual-retrieval
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
yonatangross
data-ai
llm-ai
26
high-performance-inference
High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.
yonatangross
data-ai
llm-ai
26
langgraph-checkpoints
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.
yonatangross
data-ai
llm-ai
26
llm-safety-patterns
Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.
yonatangross
data-ai