Search

Relevance-driven CPU KV-cache offload policy for stock vLLM

Report from inside your app to TellMeWhenDown — cron heartbeats and self-checks in one line.

Server-only Supabase Vault secret-store adapter for Ankhorage.

OpenAI-compatible LLM provider for @agentix-e/nl2spel

None

AI SDK v6 provider for Pi Coding Agent (supports 15+ LLM providers)

Makes any LLM behave like a regular REST API. Define the contract, specllm enforces it.

AIMEDIA.AZ AI — çox-provayderli, failover + retry-li AI Chat Model node (NVIDIA, DeepSeek və istənilən OpenAI-uyğun endpoint).

Circuit SDK core — http client, injectable config, ed25519 identity, shared types.

Research-data storage triage: read-only stat-only scan + referenced-file-aware rotation of versioned build artifacts (e.g. SIF images)

Kryten LLM integration service - provides AI chat responses and interactions

Cloudflare Workers AI nodes for n8n, starting with a Cloudflare Chat Model.

An open-source AI framework with Groq, FastAPI, RAG, ChromaDB and React SDK.

rulvar bridge adapter wrapping any Vercel AI SDK LanguageModelV4 as a ProviderAdapter.

Seamlessly connects the AliPay gateway to the Medusa Payment Module, enabling merchants to offer AliPay as a checkout option, authorize and capture payments, and process asynchronous status updates via webhooks.

Brainiac — local any-LLM second-brain core engine + brain CLI (Markdown truth, derived SQLite index).

Blocks secrets typed into Claude Code and stores them in the OS credential vault.

AI security scanner and runtime enforcement for LLM applications — detects prompt injection, API key leaks, unsafe output, RAG poisoning, and agent hijacking in code and live traffic.

looprun on the Vercel AI SDK — RESERVED (not implemented). The backend seam contract lives in @looprun-ai/core; @looprun-ai/mastra is the v0 backend.

OpenAI OAuth provider for AI SDK 7 and TanStack AI backed by the Codex Responses endpoint