Search

Python SDK for persistent, character-driven simulations with action/event rules and optional LLM interact loops.

OpenFrame Microservice Suite — Qdrant vector-store adapter.

Isolated secure launcher for LoopGrid's Claude Code plugin

Replays real LLM provider responses through LLM SDKs and checks whether each SDK reports what actually happened.

OpenAI-compatible wire dialect extension for the Stack dialects registry.

openai-api provider-route extension for the Stack `providers` registry.

vllm provider-route extension for the Stack `providers` registry.

Image drag-drop settings surface: the tweaks-drag-drop section (enable + max image bytes) consumed by the client attachment seam.

Agent Proxy 的 llm-bridge 协议转换与流式处理接口。

Testing framework for Tcl: test runner, assertions, mocking and line/branch coverage

Temporary package placeholder for staged publishing

Temporary package placeholder for staged publishing

Temporary package placeholder for staged publishing

基于大模型的识图能力，粘贴截图，框选区域，按模板识别成可复制的文字

How much each source (CLAUDE.md, rules, skills, memory, tool results) costs in the context of a Claude Code session, counted from the API usage in its transcript.

Deriva is a research project aimed at enabling digital architects by automating the derivation of enterprise architecture models. Deriva uses dual knowledge graphs, heuristics and LLM's.

DaYan (大衍): thought-graph modeling, process-level evaluation, pattern mining and verified data augmentation for LLM reasoning

Brew any document into LLM-ready Markdown: PDF tables, spreadsheets, docx - no ML, deterministic, with a JSON receipt

Benchmark-driven router for OpenAI-compatible LLM endpoints

Temporary package placeholder for staged publishing