genpark-context-window-lost-in-middle-reorderer-skill

by Alpha-Park

Overview Schema Source Related Servers Discussions Admin

Python

Local

Related Servers

Alternatives to genpark-context-window-lost-in-middle-reorderer-skill

No user-submitted related servers found.

Related Servers

genpark-cosine-bm25-reciprocalofficial
RAG Systems Knowledge & Memory
alphaparkinc
A
license
Not graded
quality
B
maintenance
Enables hybrid retrieval over agent memory and documents by fusing BM25 lexical and cosine vector rankings with reciprocal rank fusion, plus knowledge graph expansion, semantic caching, and context reordering for RAG.
Updated 12 hours ago (2026-09-28 02:54 UTC)
7
MIT
genpark-knowledge-graph-entityofficial
Knowledge & Memory
Alpha-Park
A
license
Not graded
quality
B
maintenance
Enables agents to build and query structured semantic graphs, extracting, traversing and multi-hop reasoning over entity-relation-object triples while producing Cypher and JSON-LD graph output. It also combines BM25 lexical and dense vector retrieval with rank fusion, semantic caching and context reordering for grounded agentic memory.
Updated 12 hours ago (2026-09-28 02:56 UTC)
7
MIT
genpark-agent-hierarchicalofficial
Knowledge & Memory RAG Systems
alphaparkinc
A
license
Not graded
quality
B
maintenance
Enables agents to maintain multi-tier memory across working scratchpad, dialogue buffer, and episodic stores with recency decay. Supports hybrid BM25/vector retrieval, rank fusion, graph expansion, and context reordering for optimized MCP-based memory and RAG workflows.
Updated 12 hours ago (2026-09-28 02:53 UTC)
7
MIT
genpark-context-window-lost-inofficial
RAG Systems Knowledge & Memory
alphaparkinc
A
license
Not graded
quality
B
maintenance
Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.
Updated 12 hours ago (2026-09-28 02:58 UTC)
7
MIT
Apollo
RAG Systems Search Research & Data
Parth-Dhola
A
license
B
quality
B
maintenance
Enables AI agents to retrieve clean, anti-poisoned research context from academic papers, GitHub repositories, and web search, with built-in prompt injection defenses and zero-cost reranking.
Updated 23 days ago (2026-09-06 00:38 UTC)
6
GPL 3.0
Document RAG MCP
RAG Systems Vector Databases Search
nongtiensonpro
F
license
A
quality
B
maintenance
Provides AI agents with multi-format document indexing, hybrid dense and sparse search with reranking, and relational SQL querying over extracted tables.
Updated a month ago (2026-08-30 03:56 UTC)
12
-