STATE-Bench
Benchmark AI Agents on Enterprise Workflows
microsoft/STATE-Bench
View on GitHub ↗Benchmark AI Agents on Enterprise Workflows
STATE-Bench grew +10.9% in the last 30 days, ranks 677th of 872 in Evaluation & Guardrails, last commit 109 days ago.
Star trajectory
30 days tracked+10.9% in 30d, above the Evaluation & Guardrails median of +1.4%.
Last commit 109 days ago, staler than the median of 15d.
How it compares in Evaluation & Guardrails
Ranked 677th of 872 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere STATE-Bench sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10…
+0 (+0.0%) in 30d · Committed 166d ago · TeX · Other license
Shares Evaluation & Guardrails
Learning to Recover from LLM Agent Failures at Test Time
+861 (+237%) in 30d · Committed yesterday · Python · MIT
Shares Evaluation & Guardrails
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
+6 (+1.2%) in 30d · Committed 410d ago · Python
Shares Evaluation & Guardrails
LLM Agent and Evaluation Framework for Autonomous Penetration Testing
+5 (+1.6%) in 30d · Committed 515d ago · Python · AGPL-3.0
Shares Evaluation & Guardrails
Agent harness framework for building, running, and verifying LLM workflows
+2 (+0.8%) in 30d · Committed 190d ago · TypeScript · Apache-2.0
Shares Evaluation & Guardrails
An agent harness built for teaching: ~1,400 lines of Python with goal mode, permissions, skills, MCP and…
Committed 14d ago · Python · MIT
Shares Evaluation & Guardrails
Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution…
+0 (+0.0%) in 30d · Committed 124d ago · Python
Shares Evaluation & Guardrails
Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"
+2 (+1.8%) in 30d · Committed 873d ago · Python
Shares Evaluation & Guardrails
Verification-gated skill routing and self-improvement harness for Hermes-style agent skills
+0 (+0.0%) in 30d · Committed 57d ago · Python · MIT
Shares Evaluation & Guardrails
Open-source plugin for designing and reviewing software with agents
+21.8k (+11650%) in 30d · Committed today · Python · Apache-2.0
Shares Evaluation & Guardrails
- Language
- Python
- License
- MIT License
- Contributors
- 2
- Forks
- 15
- Watchers
- 0
- Open issues
- 9
- Releases
- 6
- Created
- 2026-05-11
- Stars this week
- +2
You've seen where STATE-Bench stands today.
Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.