Wiki Knowledge Sources for AgentsMake project wikis readable by coding agents.
Run llmwiki-serve beside an existing LLMWiki, Markdown, or Obsidian folder. Agents retrieve project context over HTTP and MCP. Bridge and chat stay optional.
Skip to content
60-second demo
See the folder-to-agent flow before you install.
Upstream workflows create compatible Markdown or wiki files. llmwiki-serve projects that folder read-only, and agents, bridge, or chat consume the served Knowledge Source.
Use the folder you already haveKeep project knowledge in its current LLMWiki, Markdown, or Obsidian folder. Serve it read-only instead of migrating it into a hosted RAG app.Let agents pull focused contextCoding agents and scripts can query page, search, context, graph, HTTP, and MCP surfaces before planning edits or answering.Add orchestration only when neededUse the bridge for multi-source evidence and runtime-backed answers. Use chat to test connections, citations, traces, and graph context.
Public preview for AX and coding-agent workflows
Turn scattered project wikis into local Knowledge Sources.
These components are for teams that already have project knowledge spread across LLMWiki, Markdown, or Obsidian folders. Instead of combining everything into one large RAG application, run a small source server beside each folder and let the coding agent retrieve the context it needs.
The default path is intentionally small: serve one folder, verify the served view, and connect it to Codex, Claude Code, Copilot-style agents, IDE extensions, or scripts. Bridge and chat are optional layers for multi-source evidence, runtime delegation, and human inspection.
Use it when you want to...
- Reuse an existing project wiki without moving the files.
- Give a coding agent project-specific memory on demand.
- Keep evidence, citations, and graph context visible during agent work.
- Connect several wiki folders only when one workflow needs them together.
Minimum useful pathRun
llmwiki-serve on your own wiki folder or ./examples/sample-wiki, then query /query. Stop there if direct retrieval is enough.Public-preview installUse source checkouts today. PyPI and npm package commands become primary after publication gates pass.
Protocol postureSource access is HTTP/MCP first. A2A source compatibility is opt-in, and bridge runtime surfaces are described as A2A-style and MCP-style compatibility.
First Run At A Glance
Step 1Start your source
Serve an existing wiki folder, or use ./examples/sample-wiki for a known-good smoke.
Call /health, /manifest, and /query. Stop here if direct retrieval is enough.
Use evidence-only source fan-out first. Connect a runtime only when the bridge should synthesize answers.
OptionalOpen chatTest the source and bridge, ask a question, then inspect citations, graph context, artifacts, and run details.
Repositories
Knowledge Sourcellmwiki-serve
Serves one existing LLMWiki, Markdown, or Obsidian folder as read-only HTTP/MCP context, search, page, graph, and manifest APIs.
Optional coordinatorllmwiki-agent-bridgeConnects one or more sources, gathers cited evidence, optionally delegates synthesis to a runtime, and returns normalized artifacts.
Optional workbenchllmwiki-chatLets humans configure sources and bridge runtimes, ask questions, and inspect citations, graph context, artifacts, and traces.
When To Add Bridge Or Chat
| Need | Recommended path |
|---|---|
| One coding agent should read one wiki folder while it works | Run llmwiki-serve and connect the agent directly. |
| Several wiki folders must be searched together | Run one llmwiki-serve per folder and connect them through llmwiki-agent-bridge. |
| A service should gather evidence and call a model runtime for a cited answer | Use llmwiki-agent-bridge in delegated-runtime or hybrid mode. |
| A human needs to test setup, inspect evidence, or debug traces | Open llmwiki-chat as the browser workbench. |
| You only need package status, release support, or protocol details | Read Release Status, Protocols, and API Reference. |
Module Map
flowchart LR wiki["Wiki folder"] serve["llmwiki-serve"] agent["Host agent"] bridge["Agent bridge"] runtime["Runtime"] chat["llmwiki-chat"] wiki -->|project| serve serve -->|direct retrieval| agent bridge -->|query sources| serve bridge -->|delegate synthesis| runtime chat -->|configure runtime| bridge chat -->|inspect source| serve
| Module | Owns | Does not own |
|---|---|---|
llmwiki-serve | File projection, manifest, context packs, search, read, graph, HTTP, MCP, optional A2A source compatibility. | Wiki authoring, ingestion jobs, model calls, answer synthesis, browser UI. |
llmwiki-agent-bridge | Source fan-out, runtime profile config, OpenAI-compatible chat completions call, normalized answer artifact, citations, graph, trace. | Reading local files directly, hosting a model, browser source selection UI. |
llmwiki-chat | Source setup, bridge/runtime setup, graph inspection, answer review, run details, citation selection. | Serving wiki files, storing provider secrets, production answer quality. |
llmwiki-docs | Cross-repo first-run path, architecture, protocol posture, release status, operations references. | Package runtime behavior or upstream LLM Wiki specification ownership. |
Choose Your Path
First 10 minutesServe and query a wiki
Use your existing graph, or start with the bundled sample for the fastest known-good smoke.
Codex, Claude Code, IDE agentsCall the source directlyBest when the agent can retrieve context and do its own planning, editing, and synthesis.
Hermes, DeepAgents, local runtimesAdd the Agent BridgeUse the bridge when one service should gather source evidence and return a model-backed answer artifact.
Private or team networkCheck exposure boundariesReview loopback defaults, private HTTP, CORS, source policy, bearer tokens, and TLS before sharing endpoints.
What To Read Next
| Goal | Page |
|---|---|
| Run the first local path | Quickstart |
| Understand the data flow | Demo and Data Flow |
| Understand the vocabulary | Core Concepts |
| Decide direct source vs bridge vs chat | Architecture and Runtime Adapters |
| Connect Codex, Claude Code, Copilot-style IDE agents, or scripts | Direct Agent Integrations and AI Tool Support |
| Understand HTTP, MCP, and A2A-style compatibility surfaces | Protocols and API Reference |
| Expose endpoints beyond loopback | Network & Security and Deployment |
| Check package/public-preview status | Release Status & Compatibility |
| Prepare endpoint operations | Deployment, Network & Security, and Troubleshooting |
| Check public-preview support status | Release Status & Compatibility and FAQ |
Public preview
This is independent community tooling for LLM Wiki-style Markdown knowledge folders and agent-readable context. It is not an official project from Andrej Karpathy or any upstream producer named in compatibility examples, and it does not claim certified MCP or A2A conformance.