Feather agent harness, training integrations, and evaluation tools for knowledge work
Repository Index
47,133 repositories indexed
49–68 of 68 · Most stars
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
Integrate ChatGPT-style LLMs into Neovim: ask questions, keep multi-file context, pull diagnostics / command output, and chat without leaving your editor. Highly configurable, async, lua-only plugin.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok.
- abliterated-models
- ai-api
- ai-jailbreaks
- anthropic-compatible
GPTModels - a multi model, window based LLM AI plugin for neovim, with an emphasis on stability and clean code
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
- agent-evaluation
- evaluation-framework
- evaluation-metrics
- java
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
- bland
- dspy
- livekit
- llm
You need customized prompts for your tasks! 🤏SimpleGPT is a Vim plugin designed to provide a simple yet flexible way to customize your prompts for your tasks or building chat on nearly all kinds of LLM APIs.
The E2E AI testing tool | No ML Overhead
Persistent AI workflows for Neovim. OpenAI Codex and xAI Grok integration for Neovim with persistent sessions, workspaces and token monitoring.
Effortless Natural Language Generation: Ollama, Anthropic (Calude), ChatGTP
Minimalist command based AI plugin to interact with LLM backends like Ollama and OpenAI with a powerful template system
Neovim completion for local agent commands and skills, with env-gated Claude/Codex editor integration
- blink-cmp
- claude-code
- codex
- completion
Neovim plugin for llm CLI
Run agentic TUIs inside Neovim with persistent float/panel views and editor-context helpers.
- agentic-ai
- agentic-workflow
- agents
- claude
Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.
- ai-agents
- ai-testing
- llm
- llm-evaluation
translator powered by LLm
Framework-agnostic evaluation harness for Go — test your MCP servers and AI agents with scored, CI-ready checks.