Back to directory

Wavefront

An open-source enterprise AI middleware platform for connecting APIs, databases and file storage to any LLM, and building authenticated, observable AI agents and workflows on top of the flo-ai framework.

Wavefront

Wavefront is a middleware platform for building production AI applications: it connects to APIs, databases and file storage systems and to any LLM or small language model, and provides authentication, authorization, observability and evaluation for the resulting agents and workflows. It is presented as an open-source alternative to UnifyApps, Lyzr, SuperAGI and AgentGPT, and to workflow tools such as n8n, for enterprise-grade AI automation.

It offers native SSO integrations with Google and Microsoft Entra, role-based access control down to individual agents and data sources, and OpenTelemetry-based observability that can push to Jaeger, Azure Application Insights, AWS X-Ray or any OTLP-compatible backend. It is built on the MIT-licensed flo-ai framework; Wavefront itself is licensed under AGPL-3.0 and is currently in beta.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.