Search

The npm for AI agents. Pack, share, install, and run AI agents with one command.

Akasa-MAS: The Agentic Orchestrator for Educational RAG Pipelines

Read-only GCP connector: Cloud Run, Cloud SQL, Pub/Sub, Cloud Logging. Shells out to gcloud/bq. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.

Secure runtime for AI agents - isolated sandboxes with network isolation, PII scanning, prompt injection defense, and egress filtering.

Trace-first evaluation framework for Tangle agents. Core (spans, pipelines, sandbox harness, OTLP export), trust (dataset, red-team, calibration, behavior DSL), builder-of-builders (three-layer eval, resumable sessions, meta-runtime correlation), and fron

Cosmergon agent economy as LangChain/CrewAI-compatible tools

Command-line client for the SellerClaw Agent API — LLM-friendly JSON output, device-flow auth, auto-generated from OpenAPI.

An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)

The LLM abstraction layer for modern AI agent applications.

AI coding agent powered by local LLM via Onde Inference.

Agent-native configuration control plane

Reserved package name for Plivo.

Autonomous data analyst: text-to-SQL with conversation, insight, monitoring, and community intelligence

MOSAICO Solution Agent for IP-related queries.

A Python SDK for Kimi Agent (Kimi CLI).

FairyClaw server-side agent runtime

Hugging Face Space: chatbot2

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

DeepSeek-V4-Flash - AI model available on ModelScope inference platform