1,572 listed
Agents
Agents that do a job for you: coding agents in your terminal or IDE, research and browser agents, and support, sales and legal agents. Each page says how autonomous it is, where you use it, who hosts it and what it costs, with sources.
Showing 97–119 of 119
- 0.534score
pigo
smallnest
Go reimplementation of the pi coding agent with headless and REPL modes, skills, plugins and multi-provider support.
AgentBFreshness: B★ 483 - 0.532score
Linghun
linghungegeg
Local-first AI coding terminal that grounds model output in real files, tools, permission checks and verification steps.
AgentBFreshness: B★ 459 - 0.530score
openmozi
spytensor
Desktop AI agent that runs on your machine, edits project files and runs commands, and produces Word, Excel, PowerPoint and PDF files.
AgentBFreshness: B★ 445 - 0.524score
Abu-Cowork
PM-Shawn
Local-first AI desktop assistant that reads and writes files, runs commands and builds reports on your machine, with skills and IM bots.
AgentBFreshness: B★ 403 - 0.522score
deepx-code
itmisx
Single-binary, DeepSeek-native terminal coding agent with a code graph, local OCR, model routing and an OS sandbox.
AgentBFreshness: B★ 393 - 0.518score
SuperCoder
TransformerOptimus
Local-first open-source desktop coding agent that uses your own LLM key and can index repos with an optional context engine
AgentCFreshness: C★ 999 - 0.516score
maxheadbox
syxanash
Voice-activated LLM agent for Raspberry Pi that runs Ollama models fully on the device and can run custom tools.
AgentBFreshness: B★ 355 - 0.515score
klaatcode
KlaatAI
Terminal coding agent with per-request model routing across six cost tiers, a code graph and spend monitoring, served by a hosted router.
AgentBFreshness: B★ 354 - 0.512score
iFlow CLI
iFlow
Terminal coding assistant from iFlow that is scheduled to shut down on April 17, 2026.
AgentDFreshness: D★ 5.1K - 0.504score
Plandex
Plandex
Terminal AI coding agent that plans and applies changes across large projects, with a diff review sandbox.
AgentFFreshness: F★ 15.8K - 0.477score
Agent Laboratory
Samuel Schmidgall
LLM agent workflow that assists a human researcher through literature review, experiments and report writing.
AgentFFreshness: F★ 5.9K - 0.466score
crew44
getcrew44
Local-first desktop orchestrator that runs specialist coding agents such as Claude Code, Codex and Gemini in one shared workspace.
AgentCFreshness: C★ 357 - 0.450score
Augment Code
Augment Computing
Augment's Cosmos platform runs agent loops for code review, ticket-to-PR, vulnerability fixes and incident response, with a CLI and IDE plugins
AgentCFreshness: C - 0.450score
Conductor
Conductor
Mac app that runs parallel Claude Code, Codex and Cursor agents in isolated workspaces and lets you review and merge their changes.
AgentCFreshness: C - 0.450score
Exaforce
Exaforce
Agentic SOC product whose Exabots detect, triage, investigate and respond to threats, run by your team or by Exaforce.
AgentCFreshness: C - 0.450score
GitLab Duo Agent Platform
GitLab
AI agents inside GitLab for planning, coding, security and pipelines, with optional human checkpoints
AgentCFreshness: C - 0.450score
Inkeep
Inkeep
Open-source platform for building customer-facing chat agents and AI workflows, with a visual builder and TypeScript SDK.
AgentCFreshness: C - 0.450score
Junie
JetBrains
JetBrains coding agent that runs in the terminal, inside IDEs and in GitHub and GitLab, with models you bring.
AgentCFreshness: C - 0.450score
Kiro
Amazon Web Services
AWS's spec-driven coding agent that turns prompts into requirements, designs and tasks, available in IDE, CLI, web and mobile
AgentCFreshness: C - 0.450score
NeuBird Hawkeye
NeuBird
Production ops agent that investigates alerts, finds root causes and proposes fixes that engineers approve.
AgentCFreshness: C - 0.450score
Shortcut
Shortcut
Finance agent that works in Excel, the terminal and on the desktop, with on-prem deployment and SOC 2 Type II controls.
AgentCFreshness: C - 0.450score
Zencoder
Zencoder
Agent platform that plans, builds, tests and reviews code, letting you assign different models to each phase
AgentCFreshness: C - 0.412score
terminaI
Prof-Harita
Local-first CLI that plans and runs system tasks on Windows, Linux and macOS through approval-gated tools, with a local audit log.
AgentDFreshness: D★ 425