Group: GitHub Tansuasici

Sort by:Popular▼

✓Popular✓Newest

Core framework — agent lifecycle, action routing, tool registry, capabilities, streaming.

Multi-agent orchestration — groups, topologies, negotiation, workflows, debate, council, voting, auction, trust.

Vector database integrations for semantic search and RAG capabilities

Model Context Protocol (MCP) client and server — stdio, SSE, streamable HTTP transports, unified tool registry.

Observability, security, validation — OpenTelemetry, Prometheus, prompt injection detection, sandboxing, invariants.

Retrieval Augmented Generation (RAG) capabilities including document loading, text splitting, and embedding

Built-in tool catalog — web, file, database, shell, code execution, ML, text, media, email, messaging.

Agent-to-Agent (A2A) Protocol support for TnsAI framework - enables interoperability with other agent frameworks

Agent Client Protocol (ACP) support for IDE integration

Cognitive capabilities — FSM, planning, reasoning (ReAct, GoT, Causal), context management, RAG, knowledge bases.

LLM provider implementations — OpenAI, Anthropic, Google Gemini, Mistral, Ollama, AWS Bedrock, Cohere, Groq, HuggingFace, Azure OpenAI, OpenRouter, MiniMax, ZhipuAI.

AG-UI Protocol support for TnsAI framework - enables frontend integration with streaming events

Agentic web browsing capabilities for TnsAI agents using Playwright

Redis-based distributed coordination and caching for TnsAI framework

Evaluation and testing utilities for TnsAI agents and models

Evaluation framework — G-Eval, quality metrics, release gates, regression detection.

Module for discovering and invoking tools from OpenAPI specifications.

Spring Boot auto-configuration and starter for TnsAI framework

Bill of Materials for the TnsAI framework — pins every tnsai-* module to a single coherent version.

Multi-channel messaging gateway — Telegram adapter (Discord/Slack/WhatsApp planned). Extensible via ChannelAdapter SPI.