RAG
1760AI tools in the RAG category
foxworld306
Company knowledge-base (RAG) access for dsh web agents — a composer 知识库 chip (browser half) and the kb_search model tool (host half) over a static KB whitelist, with a pgvector direct backend (default) and the Open WebUI retrieval backend
...morejamieb22
Automatic task-aware context retrieval for OpenCode — finds the project docs relevant to the current conversation and injects them, no configuration.
...moreknyazevai
Abstract spill storage seam (ctx.spillStore) for the DeepSeek Harness — save oversized tool text and return a retrieval locator
...morejdunnfive
Express router helpers for exposing AgentOS RAG + HITL HTTP APIs (host-agnostic via dependency injection).
GitHub Actions
Shared capabilities for Bun + Postgres knowledge systems: ingestion, chunking, embeddings, retrieval, judgments, and the goldens that prove extractions change nothing.
...moremichaelborck
Honeyguide core: retrieval, verification, ranking and rationale. No UI assumptions.
tao1832
Floating HUD card for DeepSeek Harness Web: per-session token usage, context window pressure, and tokens per second.
piyushwadhwa
OSVA Connector Profile V1 Google Drive MCP connector (read-only file discovery, metadata, text retrieval, Workspace export, shared drives, and change tracking)
...morelvy-jsd
Browse every DeepSeek Harness tool as a directory (category -> group -> tool), load tools on demand per agent, and find/route tools and skills by intent (BM25 retrieval with a Rust sidecar). Provides the toolCatalog service for classifier, metadata, hook
...moreReact UI components for storage metadata AI enrichment: ingest console, pipeline flow viewer, document change history inspector and recent changes card, search and model-comparison workbenches, strategy board, embedding variant board, and status, health,
...moreasyntai
Asyntai AI Assistant tools for the Vercel AI SDK: answer questions from your website, add knowledge and read chat leads.
GitHub Actions
Qdrant vector database and hybrid similarity search DataProvider for svadmin
MetaHarness example — Pinecone RAG memory agent scaffold with tiered routing, MCP default-deny, and verification gate (npx @metaharness/example-pinecone my-bot)
...morehuakirax
Smart model configuration for DeepSeek Harness: add a provider baseURL + key, pull the upstream model list, auto-match wire protocol / context window / multimodal capabilities / reasoning effort from the pi-ai catalog and models.dev, and silently write it
...moreMetaHarness SDK showcase — RLS-aware Supabase data agent (anon vs service-role, pgvector RAG, verification-gated). Run: npx @metaharness/example-supabase my-bot
...moreantt0481
Hermes terminal agent with bundled runtime, Azure sign-in, memory and RAG
yashthokal
Docs CI for AI assistants: find outdated and conflicting facts in your docs, and answer questions with sources.
hphuc-dev
Local libSQL persistence for Tessar state, checkpoints and indexed vector storage.
kyr0
Hybrid lexical/vector retrieval, candidate reranking and explainable rank fusion for defuss.