Skip to content
@evalops

EvalOps

AI agents that do real work — across every team, on any model, with evaluation and governance built in.

EvalOps

EvalOps builds control-plane software for AI agent workforces. We help teams see which agents, assistants, and tools are taking action, govern what each one is allowed to do, and widen autonomy only when the evidence supports it.

What We Build

  • Visibility across AI agents, assistants, tools, and the actions they take.
  • Policy, approval, evaluation, cost, and audit rails for agentic systems.
  • Developer workflows that turn agent output into reviewable, repeatable work.
  • Governance patterns for the AI fleet companies already have in production.

Platform Services

Discover repos by topic:

Key Repos

Repo Description
platform Control-plane monorepo for services, contracts, and console UI
maestro Multi-model coding agent (TUI, IDE, Slack, GitHub)
deploy GitOps delivery: K8s manifests, Terraform, ArgoCD
hopper Marketing site

Contact

Report vulnerabilities through SECURITY.md. For general contact, use the project-specific repository or the contact path published on the EvalOps website.

Popular repositories Loading

  1. cognitive-dissonance-dspy cognitive-dissonance-dspy Public archive

    A multi-agent LLM system for detecting and resolving cognitive dissonance.

    Python 282 26

  2. dspy-0to1-guide dspy-0to1-guide Public archive

    A comprehensive 0-to-1 guide for building self-improving LLM applications with DSPy framework

    Python 223 17

  3. deep-code-reasoning-mcp deep-code-reasoning-mcp Public

    A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI

    TypeScript 107 13

  4. dspy-micro-agent dspy-micro-agent Public archive

    Minimal agent runtime built with DSPy modules and a thin Python loop. Includes CLI, FastAPI server, and eval harness with OpenAI/Ollama support.

    Python 75 7

  5. dspy-advanced-prompting dspy-advanced-prompting Public archive

    State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

    Python 60 4

  6. orbit-agent orbit-agent Public

    A brutally honest "high‑orbit" startup advisor you can text or run from the CLI. Built with DSPy, it provides opinionated, YC-style advice and financial tools for founders.

    Python 30 3

Repositories

Showing 10 of 49 repositories
  • maestro Public

    Deixic Code (formerly Maestro) — Deixic’s native Rust coding agent for CLI, TUI, headless, hosted runner, and web workflows.

    evalops/maestro's past year of commit activity
    Rust 3 1 13 11 Updated Sep 14, 2026
  • orbit-agent Public

    A brutally honest "high‑orbit" startup advisor you can text or run from the CLI. Built with DSPy, it provides opinionated, YC-style advice and financial tools for founders.

    evalops/orbit-agent's past year of commit activity
    Python 30 MIT 3 4 5 Updated Sep 14, 2026
  • ghostlight Public archive

    A macOS client for a persistent Chromium session streamed from Linux over WebRTC.

    evalops/ghostlight's past year of commit activity
    Swift 0 Apache-2.0 0 0 1 Updated Sep 13, 2026
  • keep Public

    PoC zero-trust access stack with Google SSO, Envoy, OPA, and device attestation

    evalops/keep's past year of commit activity
    Go 1 0 7 5 Updated Sep 13, 2026
  • eval2otel Public

    Library to convert AI evaluation results to OpenTelemetry GenAI semantic conventions for observability and monitoring

    evalops/eval2otel's past year of commit activity
    TypeScript 4 MIT 0 1 1 Updated Sep 13, 2026
  • deep-code-reasoning-mcp Public

    A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI

    evalops/deep-code-reasoning-mcp's past year of commit activity
    TypeScript 107 MIT 13 7 4 Updated Sep 13, 2026
  • kestrel Public

    Context-aware AI desktop assistant for macOS

    TypeScript 5 0 6 8 Updated Sep 13, 2026
  • mcp-openapi Public

    OpenAPI 3.x to MCP server bridge in TypeScript with stdio, StreamableHTTP, and SSE transports

    evalops/mcp-openapi's past year of commit activity
    TypeScript 3 MIT 0 0 4 Updated Sep 13, 2026
  • diffscope Public

    A composable code review engine for automated diff analysis

    evalops/diffscope's past year of commit activity
    Rust 13 Apache-2.0 3 52 3 Updated Sep 13, 2026
  • shared-memory-mcp Public

    Shared Memory MCP server for agentic teams - solving coordination tax with 6x token efficiency

    evalops/shared-memory-mcp's past year of commit activity
    TypeScript 7 MIT 1 6 3 Updated Sep 10, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…