>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt

RAG

1760

AI tools in the RAG category

FileTree-backed storage and retrieval substrate for agent memory and knowledge

AgentRAG
11 dir

Session-scoped context window switcher as a DSH composer control (maintained continuation of dsh-context-window-picker)

SkillRAG
1 dir

GitHub Actions

BS工程资料系统:OAG、RAG、EDP、Workbench 与文档侧栏预览的开发测试套件。

SkillRAG
1 dir

gustavogutierrez

Local semantic search engine for Alisio (LanceDB + multilingual-e5-small on ONNX) plus a Notebook app that answers only from your sources, with citations.

...more
SkillRAG
1 dir

An MCP Server for RAG Web Browser Actor

MCP ServerRAG
2061 dir

OSVA Connector Profile V1 Microsoft OneDrive MCP connector (delegated Graph v1 reads, bounded text retrieval, optional small upload when host-approved)

...more
MCP ServerRAG
1 dir

嵌入流水线的账与闸(不调模型、不联网):plan 按单批 token 上限分批并估算 token/成本/缓存命中,dedupe 两档去重(完全相同 sha256 + 近似 Jaccard,近似只给建议),cache 只存「内容 sha256 → 向量」不存原文,check 校验同库同维度与 L2 归一化、NaN 直接拒。token 估算模型显式(英 3.5 字/token、中 1.6 字/token 加权)并给误差带,单价读不到标 unknown 不填 0。零运行时依赖,含 CLI。 | Batch-em

...more
SkillRAG
1 dir

Untangle retrieval core: hybrid search (dense + deterministic BM25 + exact symbol names) with reciprocal rank fusion, explainable score breakdowns, complexity/findability filters, grep mode and deterministic output formats (spec.md §13, vision.md §1b/§1d)

...more
SkillRAG
1 dir

`@harngine/retrieval` exposes a retriever as a recorded read Tool. The retriever chooses its index, ranking method, and storage backend.

...more
SkillRAG
1 dir

GitHub Actions

Mem0 long-term memory for DeepSeek Harness: managed Platform, self-hosted server or a local SQLite store (no Python), with a visual settings page, automatic recall/capture, editable memory summary, token budgets and weekly memory hygiene.

...more
SkillRAG
21 dir

jalotis

Hinny: an embedded hybrid search database (full-text, vector and sparse retrieval with filters, in your process). Placeholder for the first public release.

...more
SkillRAG
1 dir

vu.minh.quang

RAGO native MCP and local-first retrieval for Windows, macOS and Linux

AgentRAG
1 dir

GitHub Actions

Pi extension tools for agent self-reflection: model metadata, context window usage, thinking level, and reasoning budget.

...more
SkillRAG
1 dir

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

...more
SkillRAG
1 dir

Knowledge-graph MemoryStore decorator for Loom — graph-expanded retrieval plus a traversal API, over any MemoryStore, with learned edges persisted in the store you already have.

...more
SkillRAG
1 dir

ezzabuzaid

A rule of an elt computed dataset: it cuts the text of each loaded row into chunks that each count at most a number of tokens of the embedding model's tokenizer, so each chunk can get its own vector.

...more
SkillRAG
11 dir

hakaisha

Interactive CLI personal developer assistant

SkillRAG
11 dir

Continuum: one memory plugin for DeepSeek Harness. A single SQLite store holding every source verbatim with provenance, three-way retrieval (lexical + bge-small vectors + activation decay), one prompt injection, one capture path for messages and tool trac

...more
SkillRAG
1 dir

A mutable, browser-safe retrieval index for documents an app owns: heading-aware chunks and SQLite FTS5 over any synchronous SQLite handle (node:sqlite, or sqlite-wasm on origin-private storage).

...more
SkillRAG
31 dir

Adaptive context compaction for DeepSeek Harness: derives each model's pressure threshold and retained tail from its context window and the session's measured growth.

...more
SkillRAG
1 dir