
llama.cpp
Run GGUF models through a configurable local inference engine.
Self-hosted · Free
Open profile
Run GGUF models through a configurable local inference engine.
Self-hosted · Free
Open profile
Switch model backends behind one compatible proxy endpoint.
Self-hosted · Free
Open profileRun a multimodal model for broad tasks with a large context window.
Self-hosted · Free
Open profileGive applications one interface across many model providers.
Cloud · Self-hosted · Free tier
Open profileInstall Letta Code globally and run an autonomous agent.
Cloud · Self-hosted · Free tier
Open profile
Align supplied audio with mouth motion in existing face video.
Self-hosted · Free
Open profileTrace application runs across models and versions.
Self-hosted · Cloud · Free tier
Open profileAssemble document, chat, agent, and web-fetch blocks visually.
Self-hosted · Free
Open profile
Give organisations a shared workspace for chat and assistants.
Cloud · Paid
Open profileBuild agents from reusable architectures and model integrations.
Cloud · Self-hosted · Free tier
Open profileStore text, images, and multimodal embeddings in a local vector database.
Cloud · Self-hosted · Free tier
Open profile
Generate speech locally with a lightweight Apache-2.0 model.
Self-hosted · Free
Open profileBuild reproducible data pipelines by connecting visual workflow nodes.
Self-hosted · Free
Open profileWork with a coding agent from a terminal-based Rust harness.
Self-hosted · Bring your own key
Open profileChat with locally running models through an offline-first desktop app.
Self-hosted · Free
Open profileCall open-weight models through an OpenAI-compatible inference API.
Cloud · Paid
Open profile
Generate short text-to-video clips with an open model.
Self-hosted · Free
Open profileBrowse, download, and share open models and datasets.
Cloud · Free tier
Open profileTurn a script and photo into a lip-synced presenter video.
Cloud · Paid
Open profile
Keep persistent project memory across sessions with a self-hosted agent.
Self-hosted · Free
Open profile
Load-test language-model deployments with realistic traffic patterns.
Self-hosted · Free
Open profileRun supported open-weight models through Groq's inference service.
Cloud · Free tier
Open profile