HomeProjectsArticlesPK BoardAbout
Explore Projects

WeKnora

Active
GitHub Go NOASSERTION

Description

Tencent's open-source LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG.

Key Features

  • RAG-based Quick Q&A for everyday document lookups with semantic retrieval
  • ReAct Agent autonomously orchestrating retrieval, MCP tools, and web search for complex multi-step tasks
  • Wiki Mode where agents distill raw documents into self-maintaining, interlinked markdown knowledge bases with interactive knowledge graphs
  • Multi-source ingestion from Feishu, Notion, and Yuque with 20+ LLM provider integrations
  • Enterprise-ready multi-tenant RBAC with 4-tier role matrix, per-resource ownership, and per-tenant audit logs
  • Full Langfuse observability integration for agent reasoning, token usage, and pipeline tracing

Use Cases

💡 Enterprise knowledge base construction from scattered documents with auto-syncing from team tools
💡 Building intelligent Q&A chatbots for internal teams via WeCom, Feishu, Slack, or Telegram
💡 Automated wiki generation and maintenance from raw documentation sources
💡 Multi-step research tasks requiring tool orchestration and web search capabilities
💡 Compliance-sensitive deployments requiring full data sovereignty and audit trails

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (21.2k stars)

⚠️ Limitations

  • • No clear open-source license

Tags

go rag llm framework agent database

Categories

🤖 Agent Framework 📚 RAG Tools

Quick Start

Clone the repo, configure your environment variables with LLM API keys and database settings, run `docker compose up` to start the full stack (Go backend + React frontend + vector DB), then open the Web UI to create your first knowledge base and start querying.
Visit GitHub

Related Projects

Langchain-Chatchat

38.6k · Python
Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3
  • · Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
  • · Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
  • · Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat
View full details → View on GitHub

Google ADK Go

8.7k · Go
Active A

An open-source, code-first Go toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexible tool integration, multi-turn conversation management, and streaming responses.

goagentframework +3
  • · Idiomatic Go design leveraging native concurrency and performance for cloud-native agent applications
  • · Rich tool ecosystem with pre-built tools, custom functions, and external tool integration
  • · Code-first development approach defining agent logic, tools, and orchestration directly in Go
View full details → View on GitHub

LocalAI

48.8k · Go
Active A+

Open-source AI engine to run any model — LLMs, vision, voice, image, video — on any hardware without GPU. Provides OpenAI-compatible API for fully local, privacy-first AI inference.

llmapilocal +3
  • · Composable backend architecture — Each backend (llama.cpp, vLLM, whisper.cpp, etc.) is a separate image pulled on demand
  • · OpenAI/Anthropic/ElevenLabs-compatible API — Unified API interface across all backends for seamless cloud replacement
  • · Any modality support — LLMs, vision, voice, image, and video models behind a single unified API
View full details → View on GitHub

LLocalSearch

5.9k · Go
Stale B

A completely locally running search aggregator using LLM agents. Users can ask questions and the system uses a chain of LLMs to find answers without any external API keys.

goagentrag +2
  • · Completely local operation with no API keys required — full privacy protection
  • · Recursive LLM agent chain for multi-step internet search and reasoning
  • · Live logs and source links providing transparency into agent reasoning
View full details → View on GitHub