Skip to content
@evalops

EvalOps

EvalOps is an AI testing and monitoring platform that helps engineering teams ship reliable AI features with confidence.

Popular repositories Loading

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

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

    Python 265 20

  2. dspy-micro-agent dspy-micro-agent Public

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

    Python 50 6

  3. founder-email-optimizer founder-email-optimizer Public

    DSPy-powered email optimization for startup founders: drop in your 3 best emails, get optimized outreach for new leads

    Python 32 1

  4. 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 11

  5. bandit_dspy bandit_dspy Public

    A DSPy library for security-aware LLM development using Bandit.

    Python 6 1

  6. folie-a-deux-dspy folie-a-deux-dspy Public

    Iterative LLM agreement training framework using DSPy MIPROv2 - exploring consensus formation in AI systems

    Python 5

Repositories

Showing 10 of 23 repositories
  • mocktopus Public

    🐙 Multi-armed mocks for LLM apps - Drop-in replacement for OpenAI/Anthropic APIs for deterministic testing

    evalops/mocktopus’s past year of commit activity
    Python 0 0 0 0 Updated Sep 24, 2025
  • metaethical_breach_dspy Public

    DSPy implementation for detecting metaethical breaches in AI systems through systematic evaluation of moral reasoning patterns

    evalops/metaethical_breach_dspy’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Sep 22, 2025
  • dspy-lean-prover-hint-clipping Public

    DSPy + Lean (mock) iterative prover with hint clipping; sweeps on clipping vs KL, noise, sparsity; scalable dataset generator; curated training; frozen tools.

    evalops/dspy-lean-prover-hint-clipping’s past year of commit activity
    Python 1 0 0 0 Updated Sep 18, 2025
  • EvalATS Public

    Modern, AI-powered Applicant Tracking System with evaluation focus

    evalops/EvalATS’s past year of commit activity
    TypeScript 1 0 0 0 Updated Sep 18, 2025
  • override-cascade-dspy Public

    DSPy framework for detecting and preventing safety override cascades in LLM systems. Research-grade implementation for studying when completion urgency overrides safety constraints.

    evalops/override-cascade-dspy’s past year of commit activity
    Python 4 MIT 0 0 0 Updated Sep 14, 2025
  • founder-email-optimizer Public

    DSPy-powered email optimization for startup founders: drop in your 3 best emails, get optimized outreach for new leads

    evalops/founder-email-optimizer’s past year of commit activity
    Python 32 1 0 0 Updated Sep 14, 2025
  • llmcc Public

    LLM-native compiler toolchain - implementing 'LLM ≈ probabilistic compiler' with real OpenAI integration, structured outputs, and constrained decoding

    evalops/llmcc’s past year of commit activity
    TypeScript 1 MIT 0 0 0 Updated Sep 13, 2025
  • congress-bill-search Public

    High-quality congressional bill search with hybrid BM25+vector similarity using DuckDB, TEI embeddings, and GovInfo API. Local deployment with Docker.

    evalops/congress-bill-search’s past year of commit activity
    Python 2 0 0 0 Updated Sep 11, 2025
  • 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 11 0 0 0 Updated Sep 10, 2025
  • dspy-micro-agent Public

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

    evalops/dspy-micro-agent’s past year of commit activity
    Python 50 6 0 0 Updated Sep 9, 2025

People

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