Search
@smthrs/agents
fucory
AI SDK and CLI agent adapters for Smithers
@smthrs/openapi
fucory
OpenAPI parsing and AI SDK tool generation for Smithers
ragbenchpy
chandannaidu6
Benchmark chunking and retrieval strategies on your own data: compare cost, latency, and accuracy across chunker x retriever combinations.
...moreeve-openai-imagegen
ewhauser
A Codex-style GPT Image 2 generation and editing extension for Eve agents.
@dleangen/cage-rag
dleangen
Semantic retrieval over CAGE's own structured content (RFC-0005).
tamash-playwright
qtpsudhakar
Plug and Play Self-healing for Playwright and automatically recovers broken selectors using an AI model (Ollama, OpenAI, Anthropic, or Gemini).
...moren8n-nodes-ai-image-optimizer
GitHub Actions
在自托管 n8n 中本地压缩、缩放并转换 Binary 或公共 URL 图片
@mikiguillamon/n8n-nodes-bark
GitHub Actions
n8n community node for Bark push notifications with guided operations and custom API requests.
paired-evalkit
Shanth Kumar Bugudi
Per-query eval results and paired-bootstrap significance testing for retrieval and LLM systems
create-urban-app
GitHub Actions
Scaffold a runnable Urban app (nano.app.json + processes/forms/db/workers, or a code-first defineFlow app) that runs on both Node and Deno via @nanobpm/urban. The create-react-app of Urban (ADR 0052).
...more@tailor-cms/ce-drag-drop-manifest
Studion <[email protected]> (https://github.com/tailor-cms)
Tailor CMS drag & drop manifest
@tailor-cms/ce-drag-drop-display
Studion <[email protected]> (https://github.com/tailor-cms)
Tailor CMS drag & drop end-user component
@tailor-cms/ce-drag-drop-edit
Studion <[email protected]> (https://github.com/tailor-cms)
Tailor CMS drag & drop authoring component
@tailor-cms/ce-drag-drop-server
Studion <[email protected]> (https://github.com/tailor-cms)
Tailor CMS drag & drop server component
n8n-nodes-flowy
privat655
Bidirectional, AI-friendly compiler and decompiler for n8n workflow JSON
llm-ot-cost-monitor
Roberto Rossi <[email protected]>
Local collector for LLM token usage emitted through OpenTelemetry
saive-client
Zero-friction LLM footprint reporting for saive (saive.tech) — patches OpenAI, Anthropic and Google GenAI clients to report usage asynchronously. Never sends prompt or completion content.
...morellm-trees
Mario Koddenbrock, Ricardo Knauer
Zero-shot decision tree induction and embedding using large language models
@get-gridline/ai-sdk-provider
GitHub Actions
Vercel AI SDK provider for Gridline.
byollm
toddsampson
Bring Your Own LLM — run an app's LLM jobs on your own models. ALPHA: under active development, not for production use.