Back to directory

AgentLens

AgentLens is a trust-first marketplace and workspace for AI agents where sellers publish an agent for others to rent under a time-limited contract, buyers compare execution boundaries and audit evidence, and a six-dimensional audit framework verifies trust claims.

AgentLens

AgentLens is a trust-first AI agent marketplace and workspace. Users can discover task-specific agents, compare the evidence and execution boundaries behind them, rent a supported agent, and run it using the platform's own model, search, file, artifact and audit capabilities. Renting an agent grants time-limited execution access rather than transferring its source code or ownership.

The platform's stated boundary is that AgentLens provides the underlying brain and a governed runtime while sellers provide the specialized agent, with rentals recorded through smart contracts covering time-limited access, reviews, audit records, appeals and a reputation system. This public repository is a sanitized distribution containing the public product surface, contracts, integration schemas and non-sensitive audit reference code, including a six-dimensional evaluation framework, attestation adapters, and zero-knowledge verification components; production routing, billing ledgers and credentials remain private.

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.