Search

Xuda Dashboard Controller Agent

TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforcement.

Opinionated skills, hooks, and workflows for AI agents

AI Output Safety Middleware — the seatbelt between LLMs and your systems

The official TracePilot AI SDK. Time-travel debugging, observability, and tracing for autonomous AI agents.

Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m

Production-grade multi-agent framework - TypeScript version

Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini

JavaScript SDK for checking AI agent actions before they run.

Reverie adapter for the OpenAI Agents SDK — captures tracing spans as CognitiveEvents

Local dashboard observing SDD workflows in Claude Code

LLM Agent experimentation harness for SWE tasks

Official HTTP client for the Mnemix memory + enrichment API for AI voice and chat agents.

AWI (Agent Web Interface) SDK — deterministic browser automation for AI agents

Phionyx evaluation tooling — LLM-as-judge primitive (eval-side) plus the assessment-signal vocabulary from the Phionyx Evaluation Standard v0.2.0. Producers run a judge against a (claim, evidence, rubric) triple and emit a signed Judgment envelope. Caller supplies the LLM client; no hard dependency on any provider SDK.

Agent runtime package for VibeCollab

LLM Cost Governance — budget enforcement, cost tracking, and smart model routing for AI agent fleets.

LangChain adapter for Flotilla

SQL-backed durable storage implementations for Flotilla

AI-powered security agent — watches server logs, detects threats, and executes approved fixes via Sentinel dashboard