vercel/eve

The Open Framework for Building Agents

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 51 minutes ago
Added to GitGenius on September 13th, 2026
Created on June 16th, 2026
Open Issues & Pull Requests: 858 (+6)
GitHub issues: Enabled
Number of forks: 539
Total Stargazers: 5,119 (+0)
Total Subscribers: 19 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 12.3 hours
Mean response time: 5.3 days
90th percentile: 16.5 days
Tracked items: 417

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 96% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "tools" is answered fastest, typically in about 4 hours, while "core" waits about 2 days. Almost all tracked open issues have seen activity in the last three months. Only 7% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 328
New in 7 days: 34
Closed in 7 days: 18
Avg open age: 40 days
Stale 30+ days: 186
Stale 90+ days: 0

Recent activity

Opened in 7 days: 32
Closed in 7 days: 10
Comments in 7 days: 53
Events in 7 days: 56

Top labels

  • p2 (322)
  • bug (294)
  • enhancement (258)
  • p1 (155)
  • core (120)
  • build (60)
  • api (51)
  • p0 (50)

Detailed Description

eve is a filesystem-first framework for building durable AI agents in TypeScript.

The framework addresses the challenge of creating maintainable AI agents by organizing core agent capabilities in conventional filesystem locations rather than obscuring them in opaque abstractions. This approach makes projects easier to inspect, extend, and operate. Agents are defined through a combination of markdown instructions, TypeScript tool implementations, and configuration files stored in predictable directories, allowing developers to work with familiar file-based authoring patterns.

Teams building AI agents that need to be inspected and modified by humans should consider eve if they value transparency and conventional project structure. The framework suits projects where durability and operational clarity matter—where agents need to persist state, integrate with external tools, and remain understandable to teams over time. The tool includes scaffolding to bootstrap new agents and supports adding eve to existing projects, with full documentation bundled in the npm package for offline reference.

The project maintains active community engagement through GitHub Discussions for questions and collaboration. Contributions are welcomed through a documented process, and the team handles security reports through responsible disclosure rather than public issue tracking. The framework is in beta, meaning its APIs, documentation, and behavior may evolve before general availability.