Search
Everything in the catalog
Showing 49–72 of 346
- 0.689score
OpenManus
FoundationAgents
Open-source general-purpose agent built as an invite-free alternative to Manus
AgentBFreshness: B★ 58.8K - 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 - 0.688score
Self-Operating Computer
HyperWrite (OthersideAI)
Framework that lets a multimodal model view the screen and operate a computer with mouse and keyboard actions.
AgentAFreshness: A★ 10.3K - 0.686score
feynman
Companion-Inc
Open-source CLI research agent for literature reviews, deep research and paper drafts.
AgentAFreshness: A★ 10K - 0.684score
munder-difflin
HarnessMD
Desktop harness that coordinates several terminal coding agents as one team on your own machine.
AgentAFreshness: A★ 9K - 0.683score
xiaobei
TeamWiseFlow
Content and lead-generation agent for small businesses, deployed on your own machine and run from WeChat.
AgentAFreshness: A★ 8.6K - 0.682score
PR-Agent
PR-Agent community
Open-source AI code review agent for pull requests on GitHub, GitLab, Bitbucket, Azure DevOps and Gitea.
AgentAFreshness: A★ 13.6K↓ 17.3K/wk - 0.681score
K8sGPT
K8sGPT
Open-source CLI that scans Kubernetes clusters, diagnoses problems with built-in analyzers and explains them with an LLM.
AgentAFreshness: A★ 8.3K - 0.681score
yao
YaoApp
Self-hosted workspace and task board for running your agents across the devices you own.
AgentAFreshness: A★ 8.2K - 0.680score
CyberStrikeAI
AIPentest
Self-hosted Go workspace where AI agents run security tools through MCP for authorized testing.
AgentAFreshness: A★ 8K - 0.678score
PI-Desktop
vastsa
Local-first desktop workspace for AI agents, with plugins, MCP servers and parallel sessions.
AgentAFreshness: A★ 7.2K - 0.677score
opensquilla
TokenRhythm
Token-efficient agent with a local router that picks the cheapest capable model for each turn.
AgentAFreshness: A★ 7.1K - 0.675score
ANUS
anus-dev
Terminal coding agent that sends each request to whichever free model is answering today.
AgentAFreshness: A★ 6.6K - 0.675score
Decepticon
BitterSecurity
Autonomous red-team agent with a Docker stack, terminal CLI, web dashboard and hosted option.
AgentAFreshness: A★ 6.4K - 0.674score
Everywhere
Sylinko
Desktop AI assistant that reads the on-screen context and answers from a shortcut key.
AgentAFreshness: A★ 6.3K - 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
LobsterAI
netease-youdao
Open-source desktop agent that edits files and Office documents and takes tasks from chat apps.
AgentAFreshness: A★ 6.1K - 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 - 0.672score
maka
apache
Apache-licensed agent workspace that keeps an append-only event log of every model and tool action.
AgentAFreshness: A★ 5.9K - 0.670score
rakazo
elie222
Open-source, self-hosted AI agent platform for persistent bots with their own computers and memory.
AgentAFreshness: A★ 5.6K - 0.670score
OpenMausBot
milind-soni
Open-source desktop app where AI agents appear as chat contacts, each running Claude or Codex locally.
AgentAFreshness: A★ 5.5K - 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