Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows without noise. Built for efficiency and scale.
-
Updated
Nov 8, 2026 - HTML
Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows without noise. Built for efficiency and scale.
Production-grade AI agent memory and context management platform (monorepo)
Give one OpenClaw session durable memory, topic-aware continuity, and bounded token growth.
Context Assembler DSH — DeepSeek Harness 上下文汇编插件:按话题块编排上下文,最大化每 token 互信息密度
视觉偏好互动体验:少量选择、提前猜牌、偏好学习与可回放证据。Offline-first preference playground with an evidence-gated model and optional Jev comparison.
Local Go daemon that gives AI tools persistent shared workspace state. Context assembly, multi-provider inference routing, hash-chained ledger, MCP server.
RAG Trace Debugger is an observability tool for debugging RAG pipelines. It traces retrieval, reranking, context assembly, and generation to pinpoint failure stages. It includes a React dashboard, framework-agnostic tracing SDK, LangChain/LlamaIndex adapters, and a self-healing loop for testing parameter fixes.
CA Assembler — Hermes Agent 插件版(ContextAssembler v6.x, Python):话题块上下文汇编、水位压力切割、Fct/OODA 事实提炼、reality 归并与注入、工具轮摘要。MIT。设计已延续至 CA-DSH V0.99 (i1j/ca-dsh)。
Given a bug and a token budget, how should you pick which code to show the LLM? This repo contains a benchmark that evaluates different context assembly methods on that question, using controlled single-line mutations across two Python repositories. Still in development, will expand to more methods, models and repositories.
G0 context-assembly gate for AI agents - the gate before G1: automatic tiered context loading with self-check loop (BSL 1.1)
To associate your repository with the context-assembly topic, visit your repo's landing page and select "manage topics."