1.Ikaleio / lm-detector
Model fingerprint detection with a shared Web and Bun CLI reference bank
+494 stars
from 1,200 · score 6.20
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
20 repositories by Attention Score · Oct 30, 2026 – Nov 5, 2026 (UTC)
2.promptfoo / promptfoo
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
- llm
- prompt-engineering
- prompts
- llmops
- prompt-testing
- testing
- +12 more
+281 stars
from 26,602 · score 5.64
3.lyramakesmusic / neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
+228 stars
from 1,703 · score 5.43
4.Shyboy0499 / precondition-library
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
- agent-architecture
- git-automation
- llm-agents
- program-synthesis
- research
+105 stars
from 245 · score 4.66
5.ninjahawk / livenerf
Benchmark for tracking model capability after release.
+93 stars
from 1,612 · score 4.54
6.slee-persis / GVS5H
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
+85 stars
from 1,113 · score 4.45
7.rsi-gear / gear
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
- continual-learning
- infrastructure
- +6 more
+81 stars
from 336 · score 4.41
8.MCG-NJU / AutoTavern
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
- game-ai
- hearthstone
- reinforcement-learning
- rust
+78 stars
from 167 · score 4.37
+75 stars
from 169 · score 4.33
10.EleutherAI / lm-evaluation-harness
A framework for few-shot evaluation of language models.
- evaluation-framework
- language-model
- transformer
+61 stars
from 14,347 · score 4.13
11.Ta0p1 / ResolveLab
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
+44 stars
from 62 · score 3.81
12.HuangShengZeBlueSky / dsh-harness-evolution
Evolved DSH plugin harnesses for five agent benchmarks, with versioned artifacts, evolution curves and Life-Harness comparisons
- agent-benchmark
- dsh
- harness
- leaderboard
- plugin-evolution
+41 stars
from 63 · score 3.74
13.mll-lab-nu / embodied-first-exam
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
- evaluation
- harbor
- +4 more
+21 stars
from 214 · score 3.09
+20 stars
from 430 · score 3.04
+20 stars
from 294 · score 3.04
16.microsoft / promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
- ai
- llm
- chatgpt
- gpt
- prompt
- prompt-engineering
- +2 more
+5 stars
from 11,257 · score 1.79
17.latitude-dev / latitude-llm
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
- llm-observability
- agent-monitoring
- agent-observability
- ai-error-monitor
- ai-monitoring
- ai-observability
- +2 more
+4 stars
from 4,740 · score 1.61
18.paper-instruments / feather-train
Feather agent harness, training integrations, and evaluation tools for knowledge work
+3 stars
from 226 · score 1.39
19.anthony-chaudhary / dos-kernel
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
- agent-orchestration
- cli
- developer-tools
- llm-agents
- mcp
- multi-agent
- +13 more
+1 stars
from 20 · score 0.69
20.tushariitr-19 / assay
Framework-agnostic evaluation harness for Go — test your MCP servers and AI agents with scored, CI-ready checks.
+1 stars
from 4 · score 0.69