Search
Everything in the catalog
Showing 25–48 of 234
- 0.706score
Suna
Kortix
Open-source AI operating system where agents work in cloud sandboxes and land changes through approved change requests
AgentAFreshness: A★ 20.3K - 0.705score
bolt.diy
StackBlitz Labs
Open-source AI workspace that builds full-stack web apps in the browser with any of 22+ LLM providers
AgentAFreshness: A★ 20K - 0.705score
Agent Zero
Agent Zero
Agent framework that gives the agent its own Dockerized Linux computer with a browser, projects, skills and plugins
AgentAFreshness: A★ 19.6K - 0.703score
avante.nvim
avante
Neovim plugin that gives AI code suggestions and applies them to your files, modeled on the Cursor IDE
AgentAFreshness: A★ 18.2K - 0.703score
rowboat
rowboatlabs
Open-source desktop assistant that builds a knowledge graph from your work and runs background agents on events or schedules
AgentAFreshness: A★ 18.1K - 0.701score
DeepCode
HKU Data Intelligence Lab
Open-source multi-agent coding system from the HKU Data Intelligence Lab, written in Python
AgentAFreshness: A★ 16.8K - 0.697score
cc-haha
NanmiCoder
Local-first desktop workbench for Claude Code and other agents, with worktrees, diff review, multi-model support and chat-app remote access.
AgentAFreshness: A★ 15.1K - 0.695score
OpenAI Codex
OpenAI
OpenAI's coding agent for the terminal, editor, desktop app and ChatGPT cloud, included in ChatGPT plans
AgentAFreshness: A★ 130.8K↓ 13.1M/wk - 0.694score
MiMo-Code
XiaomiMiMo
Terminal-native AI coding assistant that reads and writes code, runs commands, manages Git and keeps persistent project memory.
AgentAFreshness: A★ 13.7K - 0.693score
agent-orchestrator
OrchestratorInc
Open-source desktop workspace that runs, supervises and follows coding agents across git worktrees, from task to merged pull request.
AgentAFreshness: A★ 13.6K - 0.692score
Kimi Code CLI
Moonshot AI
Terminal coding agent from Moonshot AI that edits code and runs commands, with MCP, skills and ACP support.
AgentAFreshness: A★ 8K↓ 71.3K/wk - 0.690score
ekko-studio
EKKOLearnAI
Local-first workspace for chatting with multiple agents, coding agents and visual workflows.
AgentAFreshness: A★ 11.5K - 0.689score
Octop
TencentCloud
Self-hosted AI assistant for multiple users and agents, reachable from a web dashboard and chat apps.
AgentAFreshness: A★ 10.9K - 0.684score
munder-difflin
HarnessMD
Desktop harness that coordinates several terminal coding agents as one team on your own machine.
AgentAFreshness: A★ 9K - 0.678score
PI-Desktop
vastsa
Local-first desktop workspace for AI agents, with plugins, MCP servers and parallel sessions.
AgentAFreshness: A★ 7.2K - 0.675score
ANUS
anus-dev
Terminal coding agent that sends each request to whichever free model is answering today.
AgentAFreshness: A★ 6.6K - 0.674score
Kun
KunAgent
Local-first desktop and terminal workspace where AI agents work on code, documents and research.
AgentAFreshness: A★ 6.3K - 0.674score
mini-swe-agent
Princeton & Stanford
Minimal software engineering agent built around bash only, scoring above 74% on SWE-bench Verified.
AgentBFreshness: B★ 8.8K↓ 3.7M/wk - 0.673score
open-duet
Anil-matcha
Open-source workspace for named AI agents with memory, delegation, routines and approval controls.
AgentAFreshness: A★ 6.1K - 0.673score
superset
superset-sh
Desktop workspace for running Claude Code, Codex and other CLI coding agents in parallel git worktrees, with diffs and previews.
AgentAFreshness: A★ 15.5K - 0.668score
Mistral Vibe
Mistral AI
Open-source command-line coding assistant from Mistral that runs on Mistral models and asks approval before tool execution.
AgentAFreshness: A★ 5.2K - 0.665score
KiroCrew
kirodotdev
Open-source persistent development workspace with unattended tasks, schedules and heartbeat monitoring.
AgentAFreshness: A★ 4.6K - 0.665score
AutoDev
Phodal Huang
Multi-agent development platform built on Kotlin Multiplatform, with IDE plugins, a CLI, desktop, mobile and web targets.
AgentAFreshness: A★ 4.6K - 0.663score
command-code
CommandCodeAI
Terminal coding agent that learns from accept, reject and edit decisions through its taste model.
AgentAFreshness: A★ 4.2K