Search

SpeechifyAI text to speech for the Vercel AI SDK: generateSpeech() with Simba 3 models, speech marks included.

Integration layer for WhatsApp Cloud API with Firestore for easy message storage and management.

Self-contained web search + page-simplification provider for OpenCode's built-in websearch tool. Works with any model, including local ones.

Claude Code hook for forgd-verdict: scan prompts and tool calls before they run.

One OSS scan core, six thin adapters, for Claude Enterprise DLP control points.

Calibrated, risk-controlled early exit for reasoning LLMs — stop thinking when the answer is ready

The Sprouts Data tools (search, look-alike and entity lookup) and search retriever for LangChain.

Thin client for the Continuum AI gateway: preconfigures the official OpenAI/Anthropic SDKs with the gateway's base_url and x-continuum-* headers (project, session, memory, compression).

Serverless autocompletion engine for Rust and Python: exact, prefix, infix, abbreviation, spelling-tolerant, word-decomposing and semantic completions from object storage

Native MLX speech inference (SenseVoice, Paraformer, Whisper, Qwen3-ASR, GLM, MoSS, Fun-ASR-Nano) with W4A16 quantization, an OpenAI-compatible server and pseudo-streaming, for Apple Silicon

Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications