Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
ClawBench
Datasets & benchmarksOpen-source benchmark for browser AI agents on daily tasks.
git clone https://github.com/TIGER-AI-Lab/ClawBench.git -
ai-agents-the-definitive-guide
Agents & frameworksRepo for AI Agents The Definitive Guide
git clone https://github.com/Nicolepcx/ai-agents-the-definitive-guide.git -
GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite
git clone https://github.com/Tiger3807861189/GLM-5.3-Flash-J-Space-Capability-Realization-Report.git -
swe-sweep
Datasets & benchmarksHow many bugs can LMs find & fix in large codebases?
git clone https://github.com/facebookresearch/swe-sweep.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
opencode-skill-creator
SkillsCreate, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.
git clone https://github.com/antongulin/opencode-skill-creator.git -
agent-duel
Datasets & benchmarksBlinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.
git clone https://github.com/bottomless/agent-duel.git -
WebsiteBench
Datasets & benchmarksCan AI agents rebuild websites through browser exploration?
git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git -
overtime
Agents & frameworksGive a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In early development.
git clone https://github.com/ukanwat/overtime.git -
context-diamond
MCP serversAuditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.
git clone https://github.com/RainCherb/context-diamond.git -
self-bench
Datasets & benchmarksBenchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.
git clone https://github.com/mupt-ai/self-bench.git -
xorcise
Datasets & benchmarksRun cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.
git clone https://github.com/xorcise-ai/xorcise.git -
embodied-first-exam
Agents & frameworksThe 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.
git clone https://github.com/mll-lab-nu/embodied-first-exam.git -
DishwasherBench
Datasets & benchmarksA dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.
git clone https://github.com/composo-ai/DishwasherBench.git -
SkillCorpus
SkillsOpen-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
git clone https://github.com/EverMind-AI/SkillCorpus.git -
TrustLLM
Datasets & benchmarks[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.
git clone https://github.com/HowieHwong/TrustLLM.git -
explicit-edit-benchmark
Datasets & benchmarksBenchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.
git clone https://github.com/alexshpunt/explicit-edit-benchmark.git -
fde-gym
Datasets & benchmarksThe online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.
git clone https://github.com/deeplethe/fde-gym.git -
primitive-bench
Datasets & benchmarksThe marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.
git clone https://github.com/primitive-bench/primitive-bench.git -
multi-agents
Datasets & benchmarksMulti-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.
git clone https://github.com/BichengWang/multi-agents.git -
skillcheck
PromptsBlind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
git clone https://github.com/sx4im/skillcheck.git -
dokimi
SkillsDokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.
git clone https://github.com/intel/dokimi.git -
ultrametric
Tools & appsThe open startup repo — everything a founder needs to start and run a company in the agentic era: the comprehensive founder processes from an agentic lens, open documents, situations founders might find themselves in, law that governs the business logic, startup lore, open modules, artifacts and schema.
git clone https://github.com/ultrametricai/ultrametric.git -
eval-genius
SkillsTeach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.
git clone https://github.com/alexgreensh/eval-genius.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.