Go to file
wizardchen 3cf0be2e97 fix(embed): warn at startup when no signing key is configured
Deployments upgraded from the old .env.example keep the published example
SYSTEM_AES_KEY, which SystemHMACKey rejects since v0.8.2. Embed sessions
then fail at request time with no hint at boot.

- Log a [startup-env] warning when no usable signing key is found, and
  surface SYSTEM_SIGNING_KEY in the startup env banner.
- Name SYSTEM_SIGNING_KEY in the embed session 503 error.
- Provision the desktop signing key before printing the banner so the
  desktop build does not warn about a key it is about to create.
- Document the symptoms and fix in troubleshooting.
2026-09-24 20:29:17 +08:00
.github refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
Formula formula: update weknora-lite to 0.3.6-test 2026-04-12 03:05:05 +00:00
cli fix(agent): PUT no longer erases the avatar, and driver errors stay server-side (#3230) 2026-09-14 20:50:15 +08:00
client fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
cmd fix(embed): warn at startup when no signing key is configured 2026-09-24 20:29:17 +08:00
config fix(session): keep auto-generated titles plain text 2026-09-24 15:56:09 +08:00
dataset fix: guard against empty choices and message=None in LLM response 2026-05-18 11:02:37 +08:00
deploy Revert "chore: make Lite edition support and related configurations hidden" 2026-04-11 18:51:16 +08:00
docker chore: update BrowserSkill extension version to 0.3.1 and enhance localization support 2026-09-23 17:12:19 +08:00
docreader fix(docreader): kill timed-out converter process groups (#2990) 2026-09-23 12:02:53 +08:00
docs docs(readme): website-matched design for all four READMEs (#3679) 2026-09-24 20:16:55 +08:00
examples docs: 迁移有效文档至 website-docs 并清理旧文档 (#3580) 2026-09-22 23:25:40 +08:00
frontend fix(ui): restore inner padding on form popups (#3673) 2026-09-24 18:18:10 +08:00
helm chore: bump version to 0.8.2 2026-09-24 14:18:55 +08:00
internal fix(embed): warn at startup when no signing key is configured 2026-09-24 20:29:17 +08:00
licenses chore: remove vendored archives and unused Python helpers 2026-09-16 15:49:36 +08:00
mcp-server fix(mcp): assemble multiline SSE events before parsing 2026-09-22 20:09:02 +08:00
migrations feat(models): add system admin model catalog console (#3662) 2026-09-24 16:31:45 +08:00
miniprogram feat(miniprogram): add zh/en i18n, tab icons, and base library compatibility 2026-09-04 17:35:25 +08:00
misc add oidc 2026-03-30 11:13:44 +08:00
packages chore: prepare v0.8.0 release notes and version bump 2026-09-03 14:46:44 +08:00
scripts chore: update BrowserSkill extension version to 0.3.1 and enhance localization support 2026-09-23 17:12:19 +08:00
testdata refactor(terminology): rename user-facing tenant labels to workspace 2026-07-14 16:14:43 +08:00
tests/miniprogram feat(miniprogram): add zh/en i18n, tab icons, and base library compatibility 2026-09-04 17:35:25 +08:00
third_party/anydoc-go fix(anydoc): 升级到 0.1.9,为恶意 PDF 的解析开销加上上界 (#2720) 2026-08-16 12:30:55 +08:00
website-docs fix(embed): warn at startup when no signing key is configured 2026-09-24 20:29:17 +08:00
.air.toml feat(docparser): 引入 anydoc 引擎,在 Go 进程内解析 office 文档 2026-08-16 11:37:27 +08:00
.dockerignore feat(browser): connect local Chrome with task controls and display modes (#3180) 2026-09-11 17:59:27 +08:00
.env.example chore: update BrowserSkill extension version to 0.3.1 and enhance localization support 2026-09-23 17:12:19 +08:00
.env.lite.example docs(ollama): document embedding model config and RAM guidance (#3531) 2026-09-23 12:02:42 +08:00
.gitattributes feat(browser): connect local Chrome with task controls and display modes (#3180) 2026-09-11 17:59:27 +08:00
.gitignore feat(browser): connect local Chrome with task controls and display modes (#3180) 2026-09-11 17:59:27 +08:00
.golangci.yml fix(auth): record last-active-tenant preference on SwitchTenant (#2922) 2026-09-01 15:43:40 +08:00
CHANGELOG.md docs: date the v0.8.2 release and describe it in the READMEs 2026-09-24 14:18:55 +08:00
LICENSE fix: remove GPL converter and bundle third-party license sources 2026-09-08 15:19:10 +08:00
Makefile refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
README.md docs(readme): website-matched design for all four READMEs (#3679) 2026-09-24 20:16:55 +08:00
README_CN.md docs(readme): website-matched design for all four READMEs (#3679) 2026-09-24 20:16:55 +08:00
README_JA.md docs(readme): website-matched design for all four READMEs (#3679) 2026-09-24 20:16:55 +08:00
README_KO.md docs(readme): website-matched design for all four READMEs (#3679) 2026-09-24 20:16:55 +08:00
SECURITY.md Enhance security policy with reporting guidelines 2025-12-19 20:04:56 +08:00
THIRD_PARTY_NOTICES.md chore: remove vendored archives and unused Python helpers 2026-09-16 15:49:36 +08:00
VERSION chore: bump version to 0.8.2 2026-09-24 14:18:55 +08:00
docker-compose.dev.yml feat(security): add a whitelist-only outbound mode that refuses before DNS (#3393) 2026-09-23 12:02:06 +08:00
docker-compose.yml fix(docs): update remaining references to migrated documentation 2026-09-24 07:51:31 +08:00
go.mod refactor(asr): move the wire format into protocol packages, and cover every vendor whose docs offer ASR (#3503) 2026-09-21 13:25:27 +08:00
go.sum refactor(asr): move the wire format into protocol packages, and cover every vendor whose docs offer ASR (#3503) 2026-09-21 13:25:27 +08:00
rerank_server_demo.py Update rerank_server_demo.py 2026-03-18 18:25:05 +08:00
test_agent_config.sh refactor(terminology): rename user-facing tenant labels to workspace 2026-07-14 16:14:43 +08:00

README.md

WeKnora: find the answers, and put knowledge to work. Tencent's open-source knowledge management framework for Q&A, tasks and wikis.

Website Docs Release License Stars
WeChat Dialog Open Platform Chrome Extension ClawHub Skill npm @wxg-prc-cpg/dsh-weknora

English · 简体中文 · 日本語 · 한국어

Overview · Quick Start · What's New · Features · Clients · Docs · Development

Tencent/WeKnora | Trendshift

Overview

WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval and reasoning. It brings a team's documents together so they can be searched, reasoned over and kept up to date.

https://github.com/user-attachments/assets/19b28ce2-a62f-4f54-b289-c983576259bc

2:25 · 1080p · English narration and captions

Use RAG to look things up, the agent for multi-step tasks, and the wiki to organize knowledge. All three work on the same knowledge bases.

01 RAG: answers you can check, with hybrid search, multimodal parsing and citations. 02 Agent: tasks done with knowledge and tools, with multi-step reasoning, tool calling, skills and memory. 03 Wiki: documents organized into a wiki, with a knowledge graph and rollback.

Beyond the three modes:

  • Memory and curation: cross-session long-term memory keeps the profile, preferences and facts a user has confirmed. Folder uploads keep their directory tree, and retrieval chunks can be edited, diffed and rolled back.
  • Data sources and formats: auto-sync from Feishu wiki / Feishu Drive / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS, with more on the way. 10+ document formats including PDF, Word, images, Excel and XMind; Office files are parsed in-process by anydoc.
  • Channels and integrations: Q&A in WeCom, Feishu, Slack, Telegram and other IM apps; an embed widget for external websites; a built-in MCP Server for Cursor, Claude and other AI tools; scoped API keys with a principal model for programmatic access.
  • Models: 27 built-in vendors with a generated model catalog, including OpenAI, DeepSeek, Qwen (Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, LiteLLM and Ollama.
  • Permissions and operations: multi-workspace RBAC (four roles, per-resource ownership, per-workspace audit log), several storage instances per workspace, a runtime task-queue dashboard with worker-pool governance, and Langfuse tracing for agent steps, token usage and pipelines.
  • Deployment: LLMs, vector databases and storage backends are all swappable. Deploy locally or on a private cloud and keep the data in your own environment.

Quick Start


ONLINE
WeChat Dialog Open Platform
Manage knowledge bases online and connect Q&A to Official Accounts, Mini Programs and other WeChat scenarios.

Open the platform →

CLOUD
Tencent Cloud Lighthouse
Deploy WeKnora from an application template and run it on your own cloud server.

Deploy on Tencent Cloud →

SELF-HOSTED
Your own environment
Deploy with Docker or Kubernetes and configure models, storage and networking yourself.

Run with Docker Compose ↓

Run with Docker Compose

Requires Docker, Docker Compose and Git.

git clone https://github.com/Tencent/WeKnora.git
cd WeKnora
cp .env.example .env    # Edit .env as needed, see comments in the file
docker compose pull     # Pull the latest images
docker compose up -d    # Start core services

Then open http://localhost and follow the onboarding guide. A walkthrough with sample data is in the Quickstart.

[!TIP] To use a local Ollama model, run ollama serve > /dev/null 2>&1 & first. For the Ollama embedding model name, OLLAMA_BASE_URL, and RAM notes, see Configuration.

Service URL
Web UI http://localhost
Backend API http://localhost:8080
Langfuse Tracing http://localhost:3000

Optional services

Add --profile flags to enable additional components; multiple profiles can be combined.

Profile Adds
(default) Core services
full All features
neo4j Knowledge Graph (Neo4j)
minio Object Storage (MinIO)
langfuse Tracing (Langfuse)
docker compose --profile neo4j --profile minio pull
docker compose --profile neo4j --profile minio up -d
docker compose down     # Stop services

Upgrading

If you already have WeKnora running and downloaded a newer release:

# Set WEKNORA_VERSION in .env to the target release (e.g. 0.8.2), or keep latest
docker compose pull     # Pull images matching WEKNORA_VERSION
docker compose up -d    # Recreate containers with new images

[!NOTE] docker compose up -d alone reuses locally cached images and may leave the UI version out of sync with the release you downloaded. Read the upgrade notes before moving from v0.8.0.

Other ways to deploy

Option When to use it
Docker Compose The standard deployment above: all features, multiple services
Kubernetes (Helm) Production clusters; the chart is in helm/
Lite single binary Local or low-resource use with no external dependencies (SQLite + in-memory queue); see Lite vs. standard
Desktop app The Lite runtime with a GUI, login-free start and a macOS host sandbox; no installer is published yet, so build it from source

All options, hardware requirements and deployment topologies: Installation guide.

[!WARNING] WeKnora ships with login authentication, but for production deployments we strongly recommend that you:

  • deploy it in an internal / private network rather than on the public internet;
  • avoid exposing the service directly to public networks, to prevent information leakage;
  • configure proper firewall rules and access controls for the deployment environment;
  • regularly update to the latest version for security patches and improvements.

What's New

v0.8.2 · 2026-09-24 · release notes

Agents can operate the browser on your computer, knowledge bases can be published to other AI tools over MCP, and a running conversation can be steered, forked or rewound.

A smart-reasoning chat driving the connected Chrome through BrowserSkill, with the in-chat task preview and pause and end controls
Operate the browser on your computer
Connection details of an MCP endpoint, with its address and mcpServers configuration for Cursor and Claude Desktop
Publish knowledge bases to other AI tools
Follow-up requirements queued above the input box while an answer is being generated
Adjust a conversation while it runs
  • Local Browser (BrowserSkill): agents drive the user's own Chrome / Edge through the open-source BrowserSkill extension, with a live task preview, pause / resume and hand-off for logins and CAPTCHAs.
  • Built-in MCP Server: per-workspace /mcp/<endpoint_id> endpoints over Streamable HTTP, each with its own token, knowledge-base scope, rate limit and tool groups. The Python mcp-server/ is deprecated.
  • Conversation control: append requirements to a running turn, fork from any earlier question, rewind in place with sandbox checkpoints, and pick reasoning effort per session. Generated files are collected in a new artifacts library.
  • Sandbox: interactive terminal and graphical desktop; macOS Lite host sandbox with project folders; a sidebar Toolbox for skills, MCP services and the browser connection.
  • Models: rebuilt model catalog (27 built-in vendors with generated context-window, max-output, reasoning and vision metadata). Agent retrieval tools are consolidated into search_knowledge / read_document / list_documents.
  • Knowledge and platform: Confluence and DingTalk Docs data sources; Bocha and Serply web search; Japanese UI; per-channel IM reply language; whitelist-only outbound mode.

[!IMPORTANT] Breaking: DingTalk channels are Stream-only, and sandbox commands run as root. See the upgrade notes.

v0.8.0 · release notes

  • Skill sandbox runtime: session-persistent Docker / E2B / Cube backends with per-tenant network policy; the Local host-process backend is removed and Docker is opt-in.
  • Tenant skill catalog: install from ClawHub / SkillHub / git / zip, with per-sandbox snapshots, live progress, file browse/edit, and personal and workspace env vars.
  • Cross-session long-term memory: profile / preference / fact / task / interest, auto-extracted with user confirmation, plus search_memory.
  • Parsing and sources: in-process anydoc office parser; GitLab and Tencent IMA data sources; XMind parsing.
  • Ecosystem: official DeepSeek Harness plugin @wxg-prc-cpg/dsh-weknora; LiteLLM; Exa and Metaso web search.
  • Chat: chat artifacts, question outline and timestamps; context compaction and provider prompt-cache markers.
  • Security: OIDC JWKS verification, optional complex passwords, document auto-tagging, and broad sandbox/security hardening.
Earlier releases (v0.2.0 – v0.7.2)
  • v0.7.2 — Launched the official product documentation site (VitePress; six sections, ~50 pages covering ~360 API endpoints and ~150 environment variables, with standalone Docker/Nginx deployment, quickstart sample data and a local MCP demo); knowledge base folder tree (upload paths stored as first-class data, browse/rename/re-file documents like a file manager); chunk editing with revision history (edit retrieval chunks in the UI, per-version diff and rollback, automatic reindexing, plus custom document metadata); Wiki page revision history (snapshots + line-level diff + one-click rollback + in-browser manual editing); directly loadable file URLs via resource_urls=public / RESOURCE_URL_MODE (third-party apps render images and files without a second authenticated proxy call); Feishu Drive data source and docx sync through the blocks API; batch document tagging; MCP Server 1.1.x (migrated to the mcp 2.x high-level API, official PyPI package tencent-weknora-mcp, new create_knowledge_from_text and list_shared_knowledge_bases for 29 tools total); AWS S3 default credential chain (IAM Role / IRSA); local HTML upload parsing; QQBot markdown replies; new PR CI checks for app / frontend / docreader / mcp-server. Plus large-scale router and modelcontext refactors, rerank and chunking quality work, and broad stability fixes.
  • v0.7.1 — New Yunzhijia (云之家) IM integration (WebSocket + image messages + markdown replies); Volcengine rerank provider (with request batching) and Zhipu AI web search provider; platform-scoped API keys for control-plane automation (tenant management, system settings, runtime queues, audit logs); per-KB activity audit trail; FAQ management enhancements (filtering, tagging, export, import tracking); Langfuse OTLP/OTel tracing migration with W3C traceparent propagation; chat header actions with one-click Markdown export and wiki tool results in the references drawer; prompt-cache observability; session channel governance (admin-scoped IM/embed/API sessions); resilient Feishu large-wiki sync; and removal of the legacy Neo4j conversation-memory dependency. Plus broad slug-integrity, SSRF-transport, and state-sync hardening.
  • v0.7.0 — Fine-grained scoped API keys & principal model (capability-level grants + per-KB restriction + API integration playground); runtime task-queue observability dashboard & worker-pool governance (per-stage pools + per-model concurrency governors + failed-task inspection/retry); multi-instance storage backends (multiple storage instances per workspace, per-KB binding, default instance); session-scoped temporary attachments (async image/doc parsing + combined limits); question & follow-up suggestions; stable resource registry with LLM-context alias compaction; @Skill / @MCP mentions with scoped agent runtime; mid-conversation MCP OAuth; QQBot & Lark (Feishu International) IM integration; Redis TLS; Requesty model provider + Keenable web search; tenantless provisioning & gated self-service workspaces; admin password reset; knowledge base duplicate flow; weknora CLI v0.10. Plus broad security hardening (SSRF, secret redaction, SQL validation, IDOR).
  • v0.6.3 — Website embed widget & Integrations Center (secure-mode token exchange + rate limits); chat experience overhaul (citation popovers, RAG pipeline progress, streaming markdown); document multi-tag & batch reparse; Wiki folders & hierarchy navigation; RSS data source; MCP OAuth2; EPUB / MHTML parsing; agent model-readiness checks; model test debugger; session source filter; workspace deletion UI.
  • v0.6.2 — Per-upload process configuration with upload-confirm dialog; document reparse with process_config; weknora CLI v0.9 (bundled Agent Skills, session stop, auth/profile harmonization); KB marquee multi-select; HNSW index for 1024-dim pgvector embeddings; chat resources store refactor; Langfuse-only tracing (Jaeger removed).
  • v0.6.1 — Document parsing trace timeline (Langfuse-style span tree with stage-by-stage progress + stop-parse); OpenSearch vector store driver; declarative built-in models via YAML; system admin & consolidated platform settings + audit log; new-user onboarding guide; settings UI redesign; weknora CLI v0.7 / v0.8 (agent-first wire contract, NDJSON, --dry-run); OpenDataLoader + PaddleOCR-VL parsers; MCP server multi-transport (stdio / SSE / HTTP); per-model thinking-mode config; Tencent LKEAP rerank + native Gemini embeddings + MiniMax-M3.
  • v0.6.0 — Workspace RBAC (4-tier role matrix Owner / Admin / Contributor / Viewer + per-KB ownership + per-workspace audit log), workspace member management & multi-workspace UX, self-service workspaces; weknora CLI v0.4 GA with mcp serve; KB retrieval fan-out across vector stores; AES-256-GCM credential encryption + docreader gRPC TLS + Token; Zhipu embedder + Huawei OBS; server-side user preferences; Go 1.26.0. See Tenants & auth.
  • v0.5.2 — Wiki ingest scales to 40k-document KBs (task queue + DLQ); MCP human-in-the-loop tool approval; Anthropic / Apache Doris / Tencent VectorDB / KS3 / SearXNG backends; adaptive 3-tier chunking with live preview; global ⌘K command palette; Yuque connector + WeChat Mini Program; weknora CLI preview.
  • v0.5.1 — Knowledge-base batch management; workspace-wide IM channels overview; session search + user-scoped pinning; unified Model / Web Search / MCP settings cards; per-agent LLM timeout; desktop workspace switching.
  • v0.5.0 — Wiki Mode GA — agents auto-generate structured, interlinked Markdown wiki pages with a knowledge graph; wiki browser + visual graph in the UI.
  • v0.4.0 — WeKnora Cloud (hosted LLM + parsing); Chrome Extension; ClawHub Skill; WeChat IM; attachment processing; Azure OpenAI / Alibaba OSS; Notion connector; Baidu + Ollama web search; VectorStore management.
  • v0.3.6 — ASR (audio); Feishu data-source auto-sync; OIDC; IM quote-reply context + thread-based sessions; document summarization; Tavily search; parallel tool calling; agent @mention scope restriction.
  • v0.3.5 — Telegram / DingTalk / Mattermost IM; IM slash commands + QA queue; suggested questions; VLM auto-describe MCP tool images; Novita AI; channel tracking.
  • v0.3.4 — WeCom / Feishu / Slack IM; multimodal image support; NVIDIA model API; Weaviate; AWS S3; AES-256-GCM API-key encryption; built-in MCP service; hybrid-search optimization; final_answer tool.
  • v0.3.3 — Parent-child chunking; KB pinning; fallback response; passage cleaning for rerank; storage auto-creation; Milvus.
  • v0.3.2 — Knowledge Search entry; per-source parser & storage engine config; image rendering in local storage; document preview; Volcengine TOS; Mermaid rendering; batch session management; memory graph preview.
  • v0.3.0 — Shared Space; Agent Skills + sandboxed execution; custom agents; Data Analyst agent; thinking mode; Bing / Google web search; API Key auth; Helm chart; Korean i18n; Qdrant.
  • v0.2.0 — Agent Mode (ReACT); multi-type knowledge bases (FAQ + document); conversation strategy config; DuckDuckGo web search; MCP tool integration; new UI with agent mode switching; MQ async task management.

Full history: CHANGELOG.md.

Product Tour

Quick Q&A and smart reasoning

Two ways to ask. Quick Q&A answers from the knowledge base with RAG and cites the sources it used. In smart reasoning the agent plans multi-step work, searching, reading documents and calling tools and skills, and shows each step in the conversation. Docs →

Quick Q&A and smart reasoning

Local browser

Operate the browser on your computer. Through Tencent's open-source BrowserSkill extension, the agent opens pages and fills in forms in your own Chrome or Edge, and hands over to you for logins and CAPTCHAs. Docs →

Local browser

Skills and sandbox

Run skills and produce files. Docker, E2B and Cube backends are supported. Turns in the same session share one workspace, and generated files can be previewed and downloaded. Open the graphical desktop or interactive terminal beside the chat to follow each step and take over when needed. Docs →

Skills and sandbox

Toolbox: MCP services and skills

Tools the agent can use. Connect external MCP services and choose, tool by tool, which are enabled and which calls need approval. Install skills from ClawHub, SkillHub, Git or ZIP, manage them per workspace, and reuse them across sandboxes. Docs →

Toolbox: MCP services and skills

Automatic wiki

Documents organized into a browsable wiki. With Wiki enabled, WeKnora extracts people, products and concepts from knowledge-base documents into pages with source citations, organized by directory. The knowledge graph shows how pages relate; pages can be edited directly and every change can be rolled back. Docs →

Automatic wiki

Observability

Tracing and runtime monitoring. Langfuse traces the reasoning, tool calls and token usage of each agent step. The document parsing timeline shows progress stage by stage, and the task-queue dashboard lists queued and failed tasks. Docs →

Observability

Architecture

WeKnora architecture: clients and channels connect to the WeKnora app, where RAG Q&A, agent reasoning and auto wiki share one knowledge pipeline; the app calls runtime services and stores data in PostgreSQL, Redis and optional stores

A modular pipeline from document parsing, vectorization and retrieval to LLM inference, in which every component can be replaced or extended. It runs locally or on a private cloud, and the Web UI needs no setup to get started. More: Architecture overview · RAG pipeline · Extension points.

Features

Intelligent Conversation

Docs: Agent · Wiki · Skills & sandbox · Memory · Chat experience

Capability Details
Intelligent Reasoning ReACT progressive multi-step reasoning, autonomously orchestrating knowledge retrieval, MCP tools, skill sandboxes, the local browser, and web search
Quick Q&A RAG-based Q&A over knowledge bases for fast and accurate answers
Wiki Mode Agent-driven auto-generation of structured, interlinked Markdown Wiki pages from raw documents; in-browser manual editing, page revision history, line-level diff and one-click rollback
Skill Catalog & Sandbox Workspace skill catalog (ClawHub / SkillHub / git / zip) installed onto session-persistent Docker / E2B / Cube sandboxes · shell_exec, file tools, artifacts, per-config network policy · interactive terminal and browser-based graphical desktop beside the chat · the macOS desktop app runs sessions without a pinned sandbox in an OS sandbox (Seatbelt), bound to a chosen project folder or a dated temporary workspace · Local host-process backend removed
Local Browser Agents drive the user's own Chrome / Edge through the open-source BrowserSkill extension in a dedicated task window (open pages, click, fill forms, read content), with a live preview, pause / resume / end, and hand-off to the user for logins and CAPTCHAs
Conversation Control Append requirements to a running turn, fork a conversation from any earlier question, rewind in place (resetting the sandbox workspace to the matching checkpoint), and choose reasoning effort per session
Artifacts Library A sidebar page listing every generated file across conversations, with type filters, search, date grouping and version history
Long-term Memory Cross-session memory (profile / preference / fact / task / interest) with auto-extract, user confirm, and on-demand search_memory
Tool Calling Built-in tools, MCP tools (incl. OAuth2 remote services, mid-conversation OAuth), web search · @Skill / @MCP mentions scope the agent runtime per turn · MCP tools are discovered and called on demand and can be enabled per tool
Conversation Strategy Online Prompt editing, retrieval threshold tuning, multi-turn context awareness, per-agent citation output toggle
Suggested Questions Auto-generated question suggestions and after-answer follow-ups based on knowledge base content
Temporary Attachments Session-scoped image / document uploads with async parsing for one-off Q&A, with a combined image + attachment limit
Citations & RAG Progress Inline citation popovers and a references drawer (web / KB source distinction), shared markdown rendering, and stage-by-stage RAG pipeline progress in chat
Session Management Filter and group sidebar sessions by source (Web / IM / Embed), with inline session-title rename

Knowledge Management

Docs: Knowledge bases · Parsing · Chunking · Retrieval · Knowledge graph · Data sources

Capability Details
Knowledge Base Types FAQ / Document / Wiki with folder import, URL import, multi-tag management, and online entry
Folder Tree Folder uploads keep their original directory structure, with a sidebar tree for browsing, folder rename, and re-filing documents into another folder
Chunk Editing & Revisions Edit retrieval chunks directly in the UI with per-version snapshots, diff and one-click rollback, and automatic reindexing after an edit · generated questions can be added, edited, deleted and regenerated · custom document metadata
Per-Upload Process Config Override parser, chunking, multimodal (VLM / ASR), graph extraction, and question generation per upload batch via the upload-confirm dialog or process_config API; reparse with new settings
Batch Reparse Re-queue parsing for multiple documents at once with optional per-batch process_config
Data Source Import Auto-sync from Feishu wiki / Feishu Drive / Lark / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS feeds (more coming soon); incremental and full sync
Document Formats PDF / Word / Txt / Markdown / HTML / EPUB / MHTML / Images / CSV / Excel / PPT / JSON / XMind
Auto-Tagging After parse, pick matching tags from the knowledge base's existing set without creating tags or overwriting manual ones
Retrieval Strategies BM25 sparse / Dense retrieval / GraphRAG / parent-child chunking / HNSW-accelerated pgvector (1024-dim) / multi-dimensional indexing
Knowledge Graph Turns documents into a graph of relationships between passages, giving indexing and retrieval structured support for more relevant, broader results (requires Neo4j: start the neo4j profile and set NEO4J_ENABLE=true)
Batch Selection & Tagging Marquee drag-select multiple documents in the KB list for batch reparse and batch tagging (common tags pre-selected)
E2E Testing Full-pipeline visualization with recall hit rate, BLEU / ROUGE metric evaluation

Integrations & Extensions

Docs: Models · MCP · Web search · IM · Embed · Storage

Capability Details
LLMs OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / LiteLLM / Ollama
Embeddings Ollama / BGE / GTE / Zhipu / OpenAI-compatible APIs
Vector DBs PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / Tencent VectorDB
Object Storage Local / Tencent Cloud COS / MinIO / AWS S3 (IAM Role / IRSA default credential chain) / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS · multiple storage instances per workspace with per-KB binding and a default instance
IM Channels WeCom / Feishu / Lark (Feishu International) / QQBot / Slack / Telegram / DingTalk / Mattermost / WeChat / Yunzhijia
Website Embed Publish agents via embed widget with domain allowlists, rate limits, and secure-mode token exchange
Web Search DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable / Zhipu AI / Exa / Metaso / Bocha / Serply
API Integration Scoped API keys (capability-level grants + per-KB restriction + throttled last-used tracking) with an API integration playground · MCP OAuth and embed sessions isolated per principal · resource_urls=public returns directly loadable file/image URLs, removing the second authenticated proxy call
MCP Server Built in: publish per-workspace endpoints at /mcp/<endpoint_id> (Streamable HTTP), each with its own token, knowledge-base scope, rate limit and tool groups (retrieval, ask, Wiki, opt-in write tools); the Python tencent-weknora-mcp package is deprecated

Platform

Docs: Tenants & auth · Observability · Platform admin · Async tasks

Capability Details
Deployment Local / Docker / Kubernetes (Helm) with private and offline support
UI Web UI / RESTful API / CLI (weknora) / Chrome Extension / Website Embed Widget / WeChat Mini Program · UI in Chinese / English / Japanese / Korean / Russian
Access Control Workspace RBAC with 4-tier role matrix (Owner / Admin / Contributor / Viewer), per-KB resource ownership, per-workspace audit log, invite-only workspaces, tenantless provisioning & gated self-service workspace creation, admin password reset (session revocation), cross-workspace superuser, scoped API keys
Security AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation · gRPC TLS + Token between app and docreader · Redis TLS · SSRF-safe HTTP client (data sources, URL import, redirect chains) · secret redaction in responses · skill sandbox isolation (Docker opt-in / E2B / Cube) with per-config network policy · OIDC ID-token JWKS verification · optional complex-password policy · whitelist-only outbound mode (SSRF_DNS_WHITELIST_ONLY)
Observability Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing · built-in Langfuse-style document parsing trace timeline with stage-by-stage progress · system-admin runtime task-queue dashboard (queue depth, per-model concurrency, failed-task inspection & manual retry)
Task Management MQ async tasks with per-stage worker-pool governance (core / post-process / enrichment / maintenance + elastic shared pool, plus an independent Wiki pool) and per-model background concurrency governors · automatic database migration on version upgrade
Model Management Centralized config, declarative built-in models via YAML, per-knowledge-base model selection, per-model thinking-mode and embedding-dimension overrides, interactive model test debugger, multi-workspace built-in model sharing, WeKnora Cloud hosted models and parsing · a generated model catalog fills context window, max output, reasoning levels and vision support, with a resolved-call preview and per-model protocol override

Clients and Integrations

Client What it does
CLI weknora Agent-first command line for the full API, with a curated MCP tool surface and bundled Agent Skills
Built-in MCP Server Publishes knowledge bases to Cursor, Claude and other MCP clients
Local Browser (BrowserSkill) Lets agents operate the user's own Chrome / Edge
Chrome Extension Select text, images, or entire pages in the browser and save them as knowledge entries with one click, without copy-paste or file upload
WeChat Mini Program Lightweight mobile client: configure API access, select knowledge bases, import URLs, and ask knowledge chat from WeChat
ClawHub Skill A WeKnora skill on ClawHub for document import, hybrid search and knowledge management via the REST API
DeepSeek Harness plugin Gives dsh coding agents read-only access to your documents
Website Embed Widget Publishes agents on external sites
Go SDK CRUD for knowledge bases, documents and sessions, plus SSE streaming Q&A
WeChat Dialog Open Platform Hosted Q&A built on WeKnora: upload knowledge and publish a Q&A service in WeChat without writing code

Command-Line Interface

weknora is the official CLI for driving the API from a terminal or an AI agent. It is agent-first: every command emits a stable JSON envelope by default (with typed error codes mapped to exit codes), and --format text renders for humans. It also serves a curated MCP tool surface (weknora mcp serve) and ships bundled Agent Skills.

weknora profile add prod --host https://kb.example.com --use
weknora auth login
weknora kb list
weknora link --kb my-knowledge-base    # bind the current directory
weknora doc upload notes.md
weknora chat "summarise the design doc"

For headless / CI use, set WEKNORA_API_KEY + WEKNORA_HOST and skip auth login; no credentials are written to disk. See cli/README.md for install + 5-minute quickstart and cli/AGENTS.md for the operational contract AI agents rely on.

MCP Server

WeKnora has a built-in MCP Server: create an endpoint under Settings → Publish & Integrations → MCP Server and connect clients over Streamable HTTP at /mcp/<endpoint_id>. See the MCP guide. The standalone Python server in mcp-server/ is deprecated and kept only for existing deployments.

ClawHub Skill

WeKnora ClawHub Skill is a WeKnora skill published on the ClawHub platform. Once installed, it enables document import (file / URL / Markdown), hybrid search (vector + keyword) across knowledge bases, and knowledge entry management — all through the WeKnora REST API.

  • Document Import: Upload files, import web pages, or write Markdown knowledge via the agent
  • Hybrid Search: Search within or across knowledge bases with vector + keyword retrieval
  • Knowledge Management: List, browse, edit, and delete knowledge entries programmatically
DeepSeek Harness Plugin

@wxg-prc-cpg/dsh-weknora is the official DeepSeek Harness (dsh) plugin (docs). The harness ships no retrieval, embedding or knowledge-base capability of its own, so the plugin gives a coding agent your documents: dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora, point it at a deployment, and four read-only tools appear in the agent's tool set.

  • weknora_search: hybrid retrieval returning source passages verbatim, each with a reusable knowledge_id
  • weknora_read_document: one document's passages reassembled in order, with paging
  • weknora_ask: WeKnora's own composed answer with citations, over the RAG or the ReAct pipeline
  • weknora_list_knowledge_bases: knowledge base names and ids, so the agent can scope its own search
WeChat Dialog Open Platform

The WeChat Dialog Open Platform is built on WeKnora and offers it as a hosted service:

  • Zero-code deployment: upload knowledge and publish a Q&A service in the WeChat ecosystem.
  • Question management: group frequent questions by category, with data tools that keep answers accurate and easy to maintain.
  • WeChat integration: connect Q&A to Official Accounts, Mini Programs and other WeChat scenarios.

Documentation

The full product documentation lives at weknora.weixin.qq.com/docs (in Chinese), organized as Getting Started → Architecture → Features → API → Clients → Development and covering ~360 API endpoints and ~150 environment variables.

Start here
Introduction Capabilities overview
Installation Docker Compose, Helm, Lite and desktop
Configuration Environment variables and models
Troubleshooting FAQ Common problems and fixes
API reference REST API overview
Release notes What changed in each release

Development

If you need to frequently modify code, you don't need to rebuild Docker images every time. Use fast development mode:

make dev-start      # Start infrastructure
make dev-app        # Start backend (new terminal)
make dev-frontend   # Start frontend (new terminal)
  • Frontend modifications auto hot-reload (no restart needed)
  • Backend modifications quick restart (5-10 seconds, supports Air hot-reload)
  • No need to rebuild Docker images
  • Supports IDE breakpoint debugging

See the Development guide for details.

The documentation site and product homepage are built from website-docs/. With Node.js 24, run cd website-docs && npm run setup && npm run build && npm run preview to preview both together; the unified static output serves the homepage at / and documentation at /docs/. See the directory's README for Nginx and Docker deployment.

Contributing

Welcome to submit Issues or Pull Requests.

  • Process: Fork → Create branch → Commit changes → Open PR
  • Standards: Format code with gofmt, follow Conventional Commits (feat: / fix: / docs: / test: / refactor:)
Validating your change

For a focused PR, validate the changed scope first:

git fetch origin main
git diff --check origin/main...HEAD
golangci-lint run --new-from-rev=origin/main ./...
go test ./path/to/changed/package -count=1

Run gofmt on changed Go files before committing. For frontend changes, run the relevant tests from frontend/ and use npm run type-check when the change affects TypeScript or Vue components.

The full maintainer gate remains:

make fmt
make lint
make test

make fmt formats the entire Go repository, so run it only with a clean worktree and review the resulting diff. Some full-suite tests require local infrastructure or service configuration. If a full check fails for an unrelated baseline or environment reason, include the exact command and failure in the PR while still providing passing targeted tests for your change.

Contributors

Thanks to everyone who has contributed:

Contributors

License

This project is licensed under the MIT License. You are free to use, modify, and distribute the code with proper attribution.