31 dependents
Package Description Downloads/month
Fast Multimodal Semantic Deduplication & Filtering 53K
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read 8K
Synthetic Data Quality Assurance 🔎 7K
search through files with fts5, vectors and get reranked results. Fast 6K
just a bunch of useful embeddings for scikit-learn pipelines 4K
KohakuTerrarium is a general-purpose AI agent framework and batteries-included a... 4K
Model2Vec intent engine for OVOS 2K
Collection of MCP tools and Agents to work with the deepset AI platform. Create,... 2K
A living memory system that ingests long-horizon data to infer insights, enablin... 2K
SOTA-level agent memory at zero infrastructure cost. 1K
CLI + MCP server for hybrid BM25 + semantic search over local Markdown vaults 1K
Agentic brain DB - the cognitive layer for AI agents 1K
Lightweight hybrid reranker with baked-in model artifact. 1K
Architecture guardrails management CLI — queryable store of architectural constr... 1K
796
784
Repo-native institutional memory CLI for Enterprise Architecture work. 693
Turn any Obsidian vault into a Zettelkasten graph — locally, with a dozen years ... 660
CodeMap is a CLI tool that generates optimized markdown docs and streamline Git ... 509
Build datasets using natural language 440
Pipeline components for Sci-kit learn to extract relevant features from text dat... 344
Pre-train Static Embedders 287
Blocking records for record linkage and data deduplication based on ANN algorith... 228
One guardrail for all, all guardrails for one! 112
Analyze Ableton Live sets to understand musical structure for music video screen... 103
Build datasets using natural language 88
让 Agent 记得人、记得事、记得语境,并且成本可控 87
Thrust is a library for building guardrails for your models. 83
Semantic search and document parsing tools for the command line 58
Intelligent middleware for AI agent tool orchestration 56
Parry is a library for building guardrails for your models. 50