Messaging gateway
Receive and reply through Telegram, Discord, or a generic webhook from one process.
Explore channelsSelf-hosted AI control plane
Connect real messaging channels to local and cloud models, then decide how every conversation is routed. Korvun keeps the gateway, policies, and orchestration under your control.
Verified delivery
v0.7.0 publishes six headless OS/architecture archives. The release also includes a cosign-signed checksum manifest and an SBOM for every archive.
VERSION=0.7.0
curl -LO https://github.com/Sebastian197/korvun/releases/download/v${VERSION}/korvun_${VERSION}_linux_amd64.tar.gz
curl -LO https://github.com/Sebastian197/korvun/releases/download/v${VERSION}/checksums.txt
sha256sum --check checksums.txt --ignore-missing
tar -xzf korvun_${VERSION}_linux_amd64.tar.gz
./korvun versionProduct map
Each part solves a concrete step between an incoming message and a governed model response.
Receive and reply through Telegram, Discord, or a generic webhook from one process.
Explore channelsPlace local Ollama and cloud Groq models behind the same routing layer.
Understand the modelGive each brain its own models, dispatch policy, and persona.
See the architectureConfigure how eligible models run and how Korvun chooses the response.
Open configurationCompose channels, brains, models, and validated connections on a canvas.
Meet the builderRun the gateway and builder from the packaged desktop application.
Install KorvunVerify the checksum manifest and inspect the supplied SBOM before running a binary.
Browse releasesRouting you can inspect
When a brain is marked private, cloud models are excluded from its eligible targets. The visual builder shows that exclusion as part of the graph.
Inspect the configuration referenceProduct proof
A 27-second recording of the v0.6.0 visual builder: channels, brains, models, and their connections on the canvas.
Build your first route
Start with one channel, one brain, and one model. The quickstart keeps the first configuration small and explicit.