Search

Core framework for building LLM agents: Agent, Messages, Tools, Models, Endpoints, RAG, Vector Database

AI coding assistant for your terminal — reads your project, edits code with your approval, runs your tests. Signs in with your vexai.best account; no API keys to copy.

Direction-neutral foundation for Memorix generic connectors

npm launcher for local-rag: resolves the platform-specific native binaries and runs the stdio MCP proxy or the ingestion hook writer.

Agent-focused CLI that surfaces repository documentation to improve coding-agent performance.

Pi extension: inspect the system prompt, active tools, messages, token breakdown and full LLM context in a tabbed overlay

A TSDIAPI plugin to extend API functionality with DeepSeek.

j-templates

Semantic task-to-agent routing for monomind

OHAM — OrthoHolonic Accessible Memory. Sealed-media receiver: exact CPU-only decode of .tsb containers in the browser, plus the one-tag <oham-stream> element. Addresses, not pixels.

CLI tool to initially index the full Ghost post content into an Algolia index.

HTTP engine scaffolding, packaging, and probing tools for Invokta.

Claude Skill that turns a plain-language brief into a complete, paste-ready Weavy (yambo.ai) workflow JSON. 154-node catalog, verified builders, model selection matrix and production-tested pipeline recipes.

Thinking tools for AI agents making discoveries in the life sciences

LangChain integration for Opensolr — managed Apache Solr with server-side embeddings and hybrid (BM25 + kNN) search

Composable, asynchronous orchestration for LLM and data-processing workflows.

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