Constant token budget for long-form LLM writing. Chapter 1000 costs the same as chapter 10 (61,331 → 4,396 tokens measured). Zero dependencies, runs on Cloudflare Workers.
AI-native data annotation pipeline using Dynamic In-Context Learning (ICL) routing. Leverages RAG to retrieve semantically relevant few-shot examples for long-context document chunking and targeted LLM prompting.
An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic, OpenAI, Google, xAI, Groq, local). MCP-integrated. Self-modifying agent mode (PLASTIC). Containerized deployment.
MCP server giving your AI writing assistant a constant-size memory of a long document. Chapter 1000 costs the same tokens as chapter 10. Local-only: no account, no API key, no network.
Unigen 把人类工作流编译为 AI Agent 。输入《岗前培训手册》→ 自动编译 → 得到一个弱模型也能稳定执行的 Agent。 质量上限由人类工作流决定，而不是模型能力。
FractoP - Fractal Processor for infinite-length text processing with LLMs using fractal architecture
Stop AI agents from executing valid-looking plans built from stale context.
StructAgent: Using Structured Retrieval to Replace FIFO Truncation in LLM Context Middleware
Independent evidence-bound recursive agent runtime for Pi.
Undergraduate thesis. Generative AI that creates Instagram content matched to a brand's identity, using long context injection instead of RAG.
Gemini API context optimizer using native PDF packaging — reduce reported input tokens by up to 99% in measured long-context workloads.
Add a description, image, and links to the long-context topic page so that developers can more easily learn about it.
To associate your repository with the long-context topic, visit your repo's landing page and select "manage topics."