Mithril
Orchestration engine that routes requests across LLM providers via one Ollama-compatible API.
Tested on macOS and LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:quinn-proto 0.11.17Peer minimum ACK delay can panic quinn-proto when ACK_FREQUENCY transmission is enabled (RUSTSEC-2026-0340, high, fixed in 0.11.18)
See 1 more
crates:quinn-proto 0.11.17— RUSTSEC-2026-0343 (high), fixed in 0.11.18
macOS arm64
You need first
- Keys or accounts: gemini, openai
brew install Mithril via GiacomoSaccaggi/tap
brew install GiacomoSaccaggi/tap/mithril 2>&1
Check that it works
mithril --versionThe output should contain “mithril 0.3.0”.
First thing to try
mithril fellowship init
ls -R .mithril 2>&1
cat .mithril/fellowship.yaml 2>&1 | head -n 200mithril serve --port 16180curl -s http://localhost:16180/api/tagsRun mithril serve --port 16180 to start the server, then point your client at http://localhost:16180.
Linux x86_64
You need first
- Keys or accounts: gemini, openai
Install mithril-cli via uv tool
uv tool install mithril-cli
Check that it works
mithril --version 2>&1The output should contain “mithril 1.0.0”.
First thing to try
mithril fellowship init 2>&1; echo "---EXIT:$?"; ls -R .mithril 2>&1; cat .mithril/fellowship.yaml 2>&1mithril servecurl -s http://localhost:16180/api/tags 2>&1Run mithril serve --port 16180 to start the server, then point your client at http://localhost:16180.
What it does
- Combine LLM providers behind one Ollama-compatible APITested
How to use it
- Run
mithril fellowship initto create a fellowship config in .mithril/fellowship.yaml. - Start the server with
mithril serve --port 16180. - List the available models with
curl -s http://localhost:16180/api/tags.
- Run
- Use 24 built-in file, git and web toolsTested
- Serve Ollama, OpenAI and MCP API endpointsTested
How to use it
- Start the server with
mithril serve --port 16180and check it withcurl -s http://localhost:16180/health. - List models on the OpenAI-style endpoint with
curl -s http://localhost:16180/v1/models. - List MCP tools with
curl -s -X POST http://localhost:16180/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'.
- Start the server with
- Run a team of AI models as a fellowshipNot tested
How far pickfit got
macOS arm64
- Installs
- Starts
- 3 of 4 features work
- Works offline
Linux x86_64
- Installs
- Starts
- 3 of 4 features work
- Works offline
Other systems
Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- Backend for Junie
- Backend for OpenCode
- Backend for Open WebUI
- Backend for LangChain / LlamaIndex
- MCP server for Claude Desktop
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 0.3.0
Linux x86_64
Its service answers requests
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 1.0.0
Differences the test machine hit
- README: mithril serve starts the engine on http://localhost:16180
In the test: server starts without a local model and still serves HTTP; log warns No local model found but health and tags work