Skip to content
ProgramBench

Open source alternatives to ProgramBench

200 open source apps like ProgramBench, closest match first.

Top picks

  1. A

    Appl

    Launch

    APPL is a prompt programming language that extends Python. It lets you write natural language prompts directly inside Python programs, so a prompt sits next to the code that uses it and can be reused and modified like any other part of the

    FreeOpen source

  2. E

    Evalplus

    Launch

    EvalPlus is a framework for rigorous evaluation of code that large language models synthesize. It is used with the HumanEval and MBPP coding benchmarks and provides enhanced versions called HumanEval+ and MBPP+. The project also includes Ev

    FreeOpen source

  3. W

    WritingBench

    Launch

    WritingBench: A Comprehensive Benchmark for Generative Writing

    FreeOpen source

  4. T

    The Pair

    Launch

    Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.

    FreeOpen source

  5. A

    Aacr Bench

    Launch

    An Alibaba open-source multi-language benchmark for evaluating LLMs in repository-level automatic code review, featuring an AI-assisted and expert-verified dataset.

    FreeOpen source

  6. A

    aider

    Launch

    Aider is a terminal-based AI pair programming tool. You run it in a project folder and ask, in plain language, for changes to existing code or for a new project, using LLMs such as Claude, GPT and DeepSeek, or local models. It builds a map

    FreeOpen source

More like ProgramBench

7
P

PromptScript

Prompt-as-Code for Enterprise AI

Launch
8
M

Machinist

Open source software factory infrastructure for advanced AI coding workflows

Launch
9
P

PMB

Local-first persistent memory for AI coding agents

Launch
10
G

Gem Team

Turn AI coding into an engineering process

Launch
11
Y

Your-source-to-prompt.html

Quickly and securely turn your code projects into LLM prompts

Launch
12
H

Harness Score

Your AI coding agent is only as reliable as the harness around it

Launch
13
A

Antivibe

Learn what AI writes, not just accept it

Launch
14
P

Psters_AI_Workflow

An auto-documenting, model-agnostic AI workflow for any project, framework

Launch
15
M

Meta_Kim

Governed execution layer for AI coding assistants: clarify intent

Launch
16
C

Claude Code Java

Reusable AI development infrastructure for Java projects

Launch
17
A

Auto Dev

AutoDev: the Multi-Agent coding development platform built on Kotlin

Launch
18
D

DeepSeek-Reasonix

A reliable coding agent for complex software engineering tasks

Launch
19
C

Codemap

a project brain for your AI

Launch
20
B

Bitloops

Give AI coding agents the context they need to ship production-quality software

Launch
21
D

Devcodex

Intent-driven AI coding workflow runtime for consistent context, skills

Launch
22
L

LafTools

The next generation of a AI-based toolbox designed for programmers

Launch
23
A

ASSERT

Requirement-driven evaluation harness for AI agents and LLM applications

Launch
24
C

Codex Chatgpt Bridge

A safe bridge for Codex and ChatGPT to hand off coding work, save tokens

Launch
25
O

Open Agent

Open-source AI agent that brings the power of open models directly into your

Launch
26
Q

QuantumByte

Open-source app builder engine — intent to working app

Launch
27
S

System Prompts And Models Of AI Tools

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI

Launch
28
C

CodingIT

CodinIT.dev Demo | Open-source, AI app builder prototype 🌟 Star to support…

Launch
29
A

Aide

AI-Native Developer Tools

Launch
30
S

Spec Kit ZH

Chinese-localized spec-driven development toolkit for Codex, Claude Code

Launch
31
C

ContribAI

Maintainer-governed agent for evidence-backed open-source contribution proposals

Launch
32
C

Cve Bench

CVE-Bench: A Benchmark for AI Agents’ Ability

Launch
33
1

10x

Up to 20x faster AI coding with multi-step Superpowers

Launch
34
P

Penelopa.ai

Continuous improvement for AI coding agents: Penelopa analyzes real Codex

Launch
35
X

xAI

Company → News · API docs · API console · GitHub

Launch
36
C

Codexmate

One dashboard for all your local AI coding agents

Launch
37
C

CLI Continues

resume any AI coding session in another tool

Launch
38
P

Promptulate

Lightweight Large language model automation

Launch
39
C

Codai

AI coding agent for your terminal

Launch
40
C

Codehamr

A minimal, local-first coding agent for the terminal

Launch
41
C

Codirigent

A Rust based terminal workspace for multiple AI coding CLIs in parallel

Launch
42
E

Empryo

AI coding harness for desktop, terminal and CI

Launch
43
A

AI Codex

Generate a compact codebase index for AI assistants

Launch
44
C

Continue

Open-source AI code assistant

Launch
45
B

basemind

Full AI context and content layer for coding agents over one MCP server

Launch
46
L

LeanKG

Stop Burning Tokens. Start Coding Lean

Launch
47
R

repo-harness

File-backed workflow harness for reliable Claude Code and Codex sessions

Launch
48
G

Generative AI With Langchain

Build production-ready LLM applications and advanced agents

Launch
49
M

Mantic.sh

A structural code search engine for Al agents

Launch
50
I

Ix

Understand any codebase instantly

Launch

About ProgramBench

P

ProgramBench

ProgramBench evaluates whether language models can rebuild programs from scratch

ProgramBench evaluates whether language models can rebuild programs from scratch.

Category
AI
Website
programbench.com