eva

Single-file Python agent for shell and ops work that runs against any OpenAI-compatible model, with per-directory sessions.

Agent by usepr

IndexedMIT★ 425

Write a review

Chalk Labs

Need help deploying eva?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Get started

Setup steps are in the repository. Repository

About

EVA is a single eva.py file that runs as a terminal agent for scripting, shell commands, tests and data analysis. It works with any OpenAI-compatible endpoint, including DeepSeek, OpenAI, and local models served by Ollama or vLLM, configured through three environment variables. Sessions are kept per directory; read-only shell commands run without confirmation while other commands ask first, unless -a is passed. The README is in Chinese and the project is MIT licensed.

Use cases: coding, data-analysis, devops, code-generation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: coding, data analysis, devopsREADME
Autonomy: Supervised: runs multi-step tasks, asks at checkpointsREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: deepseek, openai, ollama, vllmREADME
Open source: YesREADME
Billing: Uses your own API key, set as EVA_API_KEY; the default endpoint is DeepSeek's official API.README

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 425
Forks: 58
Open issues: 1
Last commit: Oct 12, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/usepr/eva
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get eva running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying eva?

Call Get help

Cite this page

eva. Agent Mart. https://agentmart.dev/agents/eva (last updated 2026-10-24)