| Server IP : 3.147.158.171 / Your IP : 216.73.216.88 Web Server : Apache/2.4.67 (Amazon Linux) OpenSSL/3.5.5 System : Linux ip-172-31-2-178.us-east-2.compute.internal 6.1.172-216.329.amzn2023.x86_64 #1 SMP PREEMPT_DYNAMIC Wed May 20 06:31:34 UTC 2026 x86_64 User : ec2-user ( 1000) PHP Version : 8.4.21 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : OFF Directory : /tsai/repo/api/logs/articles/ |
Upload File : |
# Tavily Search Results: Geneva
**Query:** AI coding agents updates — Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Gemini Code Assist
**Topic:** general
**Results:** 5
**Date:** 2026-07-13 00:05:41
---
## 1. Best AI coding tools in 2026 - Threads
**URL:** [https://www.threads.com/@ksenia_turingpost/post/DadWcpkGkYT/best-ai-coding-tools-in-claude-code-open-ai-codex-aider-cline-replit-agent](https://www.threads.com/@ksenia_turingpost/post/DadWcpkGkYT/best-ai-coding-tools-in-claude-code-open-ai-codex-aider-cline-replit-agent)
**Score:** 0.7730
### Summary
# Thread
172 views
ksenia_turingpost's profile picture
ksenia\_turingpost
Best AI coding tools in 2026
▪️ Claude Code ▪️ OpenAI Codex ▪️ Aider ▪️ Cline ▪️ Replit Agent ▪️ Cursor ▪️ Windsurf ▪️ Gemini Code Assist ▪️ Amazon Q Developer ▪️ Sourcegraph Cody ▪️ GitHub Copilot
+ Open-source coding models ▪️ Qwen3-Coder / Qwen3-Coder-Next ▪️ Kimi K2.7 Code ▪️ Devstral 2
There isn't one best AI coding tool - only the one that fits your workflow. Hopefully, this guide helps you find it -> turingpost.com/p/cod…
3
Log in or sign up for ThreadsSee what people are talking about and join the conversation.
Log in with username instead
### Full Content
[# Thread
172 views](/@ksenia_turingpost/post/DadWcpkGkYT/best-ai-coding-tools-in-claude-code-open-ai-codex-aider-cline-replit-agent)
[](/@ksenia_turingpost)
[ksenia\_turingpost](/@ksenia_turingpost)
Best AI coding tools in 2026
▪️ Claude Code ▪️ OpenAI Codex ▪️ Aider ▪️ Cline ▪️ Replit Agent ▪️ Cursor ▪️ Windsurf ▪️ Gemini Code Assist ▪️ Amazon Q Developer ▪️ Sourcegraph Cody ▪️ GitHub Copilot
+ Open-source coding models ▪️ Qwen3-Coder / Qwen3-Coder-Next ▪️ Kimi K2.7 Code ▪️ Devstral 2
There isn't one best AI coding tool - only the one that fits your workflow. Hopefully, this guide helps you find it -> [turingpost.com/p/cod…](https://l.threads.com/?u=https%3A%2F%2Fwww.turingpost.com%2Fp%2Fcode-assistants&e=AUBp9WUREsGkyLVoN_3YtCnO92bjkWOSc-4Igd-Ir3vL3CpNIIMhzT93p_G3EGpoeu5ls5GzQ8DUxzkvih7NjS-JIhnE7vvb0TD1MIZnFg_nX3B0ZDjKmb3996mFVI0gg1Z0AZrbNHg)
3
Log in or sign up for ThreadsSee what people are talking about and join the conversation.
[Log in with username instead](/login?show_choice_screen=false)
---
## 2. Best AI Coding Tools in 2026: Assistants, Agents, IDEs & Open Models
**URL:** [https://www.turingpost.com/p/code-assistants](https://www.turingpost.com/p/code-assistants)
**Score:** 0.7272
### Summary
### Fast choice
| Your workflow | Start with |
--- |
| Everyday coding | GitHub Copilot |
| Terminal-first agentic work | Claude Code, Codex, Aider |
| AI-native IDE | Cursor, Windsurf |
| Browser app building | Replit Agent |
| Large enterprise codebases | Sourcegraph Cody |
| AWS-heavy stack | Amazon Q Developer |
| Google Cloud stack | Gemini Code Assist |
| Open-source / local control | Cline, Aider, Qwen3-Coder, Kimi K2.7, Devstral 2 |
The best AI coding tool in 2026 depends less on “which model writes the best function?” and more on what kind of workflow you want to automate. [...] ## Best AI Coding Agents in 2026
### Claude Code
Claude Code is a terminal-first coding agent built for real software engineering. It can inspect large codebases, edit multiple files, run commands, debug issues, and handle long refactoring tasks with minimal supervision.
Claude Code Website
Claude Code GitHub
Claude Code Docs
### OpenAI Codex
OpenAI Codex has evolved into an autonomous AI agent platform powered by the GPT-5.5 architecture, providing repository-level refactoring and debugging via a dedicated desktop app, CLI, and web interface.
Codex Website
Codex GitHub
### Aider
Aider is a Git-first AI pair programmer for the terminal. It edits files, commits changes, and works directly with your repository, making it a good fit for developers who prefer the command line. [...] This website uses cookies
Read ourPrivacy policy and Terms of use for more information.
Home
Posts
Best AI Coding Tools in 2026: Assistants, Agents, IDEs & Open Models
# Best AI Coding Tools in 2026: Assistants, Agents, IDEs & Open Models
Twitter Library
Alyona Vert.
Alyona Vert.
Jul 4, 2026
Best AI coding tools compared in 2026: Claude Code, Cursor, GitHub Copilot, Aider, and open-source models including Qwen3-Coder and Devstral.
AI coding tools help developers write, debug, review, test, and ship code with LLMs, and in 2026, this means much more than autocomplete. The category includes coding assistants, AI-native IDEs, terminal agents, repo-level agents, and open-source coding models that can run locally or inside existing dev workflows.
### Full Content
This website uses cookies
Read our[Privacy policy](https://www.beehiiv.com/privacy) and [Terms of use](https://www.beehiiv.com/tou) for more information.
* [Home](/)
* [Posts](/archive)
* Best AI Coding Tools in 2026: Assistants, Agents, IDEs & Open Models
# Best AI Coding Tools in 2026: Assistants, Agents, IDEs & Open Models
[Twitter Library](/t/twitter-library)
[Alyona Vert.](https://www.turingpost.com/authors/alyona-vert)
Jul 4, 2026
Best AI coding tools compared in 2026: Claude Code, Cursor, GitHub Copilot, Aider, and open-source models including Qwen3-Coder and Devstral.
AI coding tools help developers write, debug, review, test, and ship code with LLMs, and in 2026, this means much more than autocomplete. The category includes **coding assistants, AI-native IDEs, terminal agents, repo-level agents, and open-source coding models** that can run locally or inside existing dev workflows.
These tools have moved far beyond simply suggesting the next line – they can understand project context, edit across files, run commands, inspect errors, generate tests, and review pull requests.
Now the main goal is to **find the tool that fits your workflow**. Local coding, enterprise compliance, repo-scale changes, agent automation, etc. – each needs a different setup. We'll help you understand which coding tool works best for you. →
| Tool | Category | Interface | Models | Best for | Price |
| --- | --- | --- | --- | --- | --- |
| Claude Code | Coding agent | Terminal, IDE | Claude models | Serious repo work, , debugging, refactoring | Included in Claude plans / usage-based |
| OpenAI Codex | Coding agent | Web, CLI, IDE, desktop Autonomous repo-level tasks Included in ChatGPT plans | OpenAI coding models | Autono-mous repo-level tasks | Included in ChatGPT plans |
| Aider | Coding agent | Terminal | Bring your own model | Git-first coding and commits | Open-source + model/API costs |
| Cline | Coding agent | IDE extension | Bring your own model | Open-source agent workflows | IDE agent Open-source + model/API costs |
| Replit Agent | Coding agent | Browser IDE | Replit-selected models | Fast prompt-to-app building | Free + paid Replit plans |
| Cursor | AI-native IDE | Desktop IDE | Multiple frontier models | Fast daily coding, inline edits | Free + paid plans |
| Windsurf | AI-native IDE | Desktop IDE | Multiple frontier models | Autono-mous develop-ment | Free + paid plans |
| GitHub Copilot | Coding assistant | IDE, GitHub, CLI | Multiple Copilot models | Autonomous IDE workflows | Free + paid plans |
| Gemini Code Assist | Coding assistant | IDE, Google Cloud | Gemini models | Google Cloud teams | Free / Standard / Enterprise |
| Amazon Q Developer | Coding assistant | IDE, AWS Console, CLI | Amazon Q models | AWS-heavy develop-ment | Free + Pro tier |
| Source-graph Cody | Coding assistant | IDE, web, Source-graph | Multiple LLMs | Large enterprise codebases | Enterprise / sales-led |
| Qwen3-Coder / Next | Open-weight model | Model / API / local stack | Qwen3-Coder models | Local coding agents, repo tasks | Open-weight + hosting costs |
| Kimi K2.7 Code | Open-weight model | Model / API / local stack | Kimi K2.7 Code | Long-context autonomous coding | Open-weight + hosting costs |
| Devstral 2 | Open-weight model | Model / API / local stack | Devstral 2 / Small 2 | Multi-file agentic code work | Open-weight + hosting costs |
## Best AI Coding Agents in 2026
### Claude Code
Claude Code is a terminal-first coding agent built for real software engineering. It can inspect large codebases, edit multiple files, run commands, debug issues, and handle long refactoring tasks with minimal supervision.
* Claude Code [Website](https://claude.ai/code)
* Claude Code [GitHub](https://github.com/anthropics/claude-code)
* Claude Code [Docs](https://code.claude.com/docs)
### OpenAI Codex
OpenAI Codex has evolved into an autonomous AI agent platform powered by the GPT-5.5 architecture, providing repository-level refactoring and debugging via a dedicated desktop app, CLI, and web interface.
* Codex [Website](https://openai.com/codex/)
* Codex [GitHub](https://github.com/openai/codex)
### Aider
Aider is a Git-first AI pair programmer for the terminal. It edits files, commits changes, and works directly with your repository, making it a good fit for developers who prefer the command line.
* Aider [Website](https://aider.chat)
* Aider [GitHub](https://github.com/Aider-AI/aider)
### Cline
Cline is an open-source coding agent that works directly inside your IDE. It can edit files, run terminal commands, use external tools, and complete multi-step coding tasks with user approval.
* Cline [Website](https://cline.bot)
* Cline [GitHub](https://github.com/cline/cline)
### Replit Agent
Replit Agent is bui
*[Content truncated...]*
---
## 3. Best Enterprise AI Coding Agents Reviews 2026 - Gartner
**URL:** [https://www.gartner.com/reviews/market/enterprise-ai-coding-agents](https://www.gartner.com/reviews/market/enterprise-ai-coding-agents)
**Score:** 0.7200
### Summary
Support for Model Context Protocol (MCP): Native MCP support to provide a standardized way for the agent to access tools, perform actions and retrieve project context in a consistent and governed manner
## Gartner Client Insights
Magic Quadrant for Enterprise AI Coding AgentsCritical Capabilities for Enterprise AI Coding Agents
Gartner Peer Insights 'Voice of the Customer': Enterprise AI Coding Agents
## Top Trending Products
KiroAmazon Q DeveloperClaude CodeGitHub CopilotGemini Code AssistCodexCursor [...] By Anthropic
4.7
(96 Ratings)
OVERVIEW ALTERNATIVES
Claude Code is a software developed by Anthropic that focuses on providing AI-powered coding assistance. The software is designed to help users write, understand, and improve code across various programming languages. It offers features such as code generation, code completion, and the ability to explain code snippets, aiming to support developers in enhancing productivity and reducing coding errors. Claude Code addresses business challenges related to software development by automating routine coding tasks and facilitating knowledge transfer, which can lead to faster development cycles and improved code quality.
Show More Details
- [x] Add to Compare
Image 18: Logo of Cursor
### Cursor
By Cursor
4.6
(92 Ratings)
### Full Content
[](https://www.gartner.com/peer-insights/home)
* [HOME](https://www.gartner.com/peer-insights/home)
*
CATEGORIES
* CATEGORIES
* Application Development
* [Observability Platforms](https://www.gartner.com/reviews/market/observability-platforms)
* [Integrated Development Environment (IDE) Software](https://www.gartner.com/reviews/market/integrated-development-environment-ide-software)
* [Business Orchestration and Automation Technologies](https://www.gartner.com/reviews/market/business-orchestration-and-automation-technologies)
* [Integration Platform as a Service](https://www.gartner.com/reviews/market/integration-platform-as-a-service)
* [Enterprise Agile Planning Tools](https://www.gartner.com/reviews/market/enterprise-agile-planning-tools)
* [View All](https://www.gartner.com/reviews/markets)
* Artificial Intelligence
* [AI Application Development Platforms](https://www.gartner.com/reviews/market/ai-application-development-platforms)
* [Generative AI Knowledge Management Apps/General Productivity](https://www.gartner.com/reviews/market/generative-ai-knowledge-management-apps-general-productivity)
* [Enterprise AI Coding Agents](https://www.gartner.com/reviews/market/enterprise-ai-coding-agents)
* [Conversational AI Platforms](https://www.gartner.com/reviews/market/conversational-ai-platforms)
* [Generative AI Infrastructure Providers (Transitioning to Cloud AI Infrastructure)](https://www.gartner.com/reviews/market/generative-ai-infrastructure-providers)
* [View All](https://www.gartner.com/reviews/markets)
* Cloud Computing
* [Strategic Cloud Platform Services](https://www.gartner.com/reviews/market/strategic-cloud-platform-services)
* [Backup and Data Protection Platforms](https://www.gartner.com/reviews/market/backup-and-data-protection-platforms)
* [Server Virtualization (Transitioning to Server Virtualization Platforms)](https://www.gartner.com/reviews/market/server-virtualization)
* [Cloud Database Management Systems](https://www.gartner.com/reviews/market/cloud-database-management-systems)
* [Cloud Application Platforms (Transitioning to Cloud-Native Application Platforms)](https://www.gartner.com/reviews/market/cloud-application-platforms)
* [View All](https://www.gartner.com/reviews/markets)
* Customer Relationship Management
* [Contact Center as a Service](https://www.gartner.com/reviews/market/contact-center-as-a-service)
* [CRM Customer Engagement Center](https://www.gartner.com/reviews/market/crm-customer-engagement-center)
* [Digital Experience Platforms](https://www.gartner.com/reviews/market/digital-experience-platforms)
* [Web Content Management](https://www.gartner.com/reviews/market/web-content-management)
* [AI Agents for Customer Service and Support](https://www.gartner.com/reviews/market/ai-agents-for-customer-service-and-support)
* [View All](https://www.gartner.com/reviews/markets)
* Data and Analytics
* [Analytics and Business Intelligence Platforms](https://www.gartner.com/reviews/market/analytics-business-intelligence-platforms)
* [Data Science and Machine Learning Platforms (Transitioning to AI Platforms For Data Science and Machine Learning)](https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms)
* [Data Integration Tools](https://www.gartner.com/reviews/market/data-integration-tools)
* [Decision Intelligence Platforms](https://www.gartner.com/reviews/market/decision-intelligence-platforms)
* [Agentic Analytics](https://www.gartner.com/reviews/market/agentic-analytics)
* [View All](https://www.gartner.com/reviews/markets)
* Education
* [Manager and Leadership Training](https://www.gartner.com/reviews/market/manager-and-leadership-training)
* [eLearning Authoring Tools](https://www.gartner.com/reviews/market/elearning-authoring-tools)
* [Corporate Learning Technologies](https://www.gartner.com/reviews/market/corporate-learning-technologies)
* [Higher Education Student Information System Software as a Service (Transitioning to Higher Education SaaS Student Information Systems)](https://www.gartner.com/reviews/market/higher-education-student-information-system-software-as-a-service)
* [Digital Learning Content Providers](https://www.gartner.com/reviews/market/digital-learning-content-providers)
* [View All](https://www.gartner.com/reviews/markets)
* Enterprise Networking and Communications
* [Unified Communications as a Service](https://www.gartner.com/reviews/market/unified-communications-as-a-service)
* [Edge Distribution Platforms](https://www.gart
*[Content truncated...]*
---
## 4. Top 5 CLI coding agents in 2026 - Pinggy
**URL:** [https://pinggy.io/blog/top_cli_based_ai_coding_agents](https://pinggy.io/blog/top_cli_based_ai_coding_agents)
**Score:** 0.7150
### Summary
Pinggy brand logo
Pinggy Community Forum Logo
# Top 5 CLI coding agents in 2026
cli coding agents banner
The CLI coding agent space has churned hard in the first half of 2026. Google retired Gemini CLI at I/O on May 19 and replaced it with Antigravity CLI (free/Pro/Ultra users have until June 18, 2026 before Gemini CLI stops serving requests). OpenAI shipped a Codex refresh on GPT-5.5 that several recent rankings now put at #1. Cursor launched a real Cursor CLI in January with a Cloud Handoff feature you don’t see elsewhere. Claude Code moved to Opus 4.7. And `sst/opencode` crossed 150K GitHub stars and ~6.5M monthly active developers, becoming the de facto open-source choice.
`sst/opencode` [...] ### Conclusion
The CLI coding agent space in May 2026 is dominated by four big-vendor tools (Claude Code, OpenAI Codex, Antigravity CLI, Cursor CLI) and one open-source standout (OpenCode). Aider and the rest still hold their niches but the center of gravity has shifted toward agents tied to a frontier model and a managed harness.
If you’re picking one for the first time: Claude Code on a Claude Pro/Max subscription is the lowest-risk default for daily use. If you need to run offline or own your data, OpenCode with Ollama is the obvious open-source pick. Everything else is a matter of which ecosystem you’re already in. [...] | CLI Agent | Best For | Default Model | Pricing | Key Strength |
--- ---
| Claude Code | Multi-file reasoning, long-running tasks | Claude Opus 4.7 / Sonnet 4.6 | API pay-per-use or Claude Pro/Max subscription | Reasoning quality and skill/subagent ecosystem |
| OpenAI Codex | Tight loop with GPT-5.5; agentic execution | GPT-5.5 | API pay-per-use; ChatGPT plans include quota | Top-ranked agent benchmarks in 2026 |
| Antigravity CLI | Google ecosystem; multi-agent workflows | Gemini 3 | Free for AI Pro/Ultra; enterprise via Code Assist | Shared harness with Antigravity 2.0 desktop; Skills/Hooks/Subagents |
| Cursor CLI | Cursor IDE users; long async runs | Auto-routes (Claude / GPT / Gemini) | Bundled with Cursor Pro ($20/mo) and above | Plan/Ask modes, Cloud Handoff with `&` prefix |
### Full Content
# Top 5 CLI coding agents in 2026
The CLI coding agent space has churned hard in the first half of 2026. Google retired Gemini CLI at I/O on May 19 and replaced it with **Antigravity CLI** (free/Pro/Ultra users have until **June 18, 2026** before Gemini CLI stops serving requests). OpenAI shipped a Codex refresh on **GPT-5.5** that several recent rankings now put at #1. Cursor launched a real **Cursor CLI** in January with a Cloud Handoff feature you don’t see elsewhere. Claude Code moved to **Opus 4.7**. And `sst/opencode` crossed **150K GitHub stars** and ~6.5M monthly active developers, becoming the de facto open-source choice.
`sst/opencode`
If you read this blog earlier in the year, the top 5 has shuffled. This update reflects what’s actually being used and discussed in May 2026 - what’s still standing, what got bumped, and the new entrants worth your time.
### Comparison Table for Top CLI Coding Agents
| CLI Agent | Best For | Default Model | Pricing | Key Strength |
| --- | --- | --- | --- | --- |
| **Claude Code** | Multi-file reasoning, long-running tasks | Claude Opus 4.7 / Sonnet 4.6 | API pay-per-use or Claude Pro/Max subscription | Reasoning quality and skill/subagent ecosystem |
| **OpenAI Codex** | Tight loop with GPT-5.5; agentic execution | GPT-5.5 | API pay-per-use; ChatGPT plans include quota | Top-ranked agent benchmarks in 2026 |
| **Antigravity CLI** | Google ecosystem; multi-agent workflows | Gemini 3 | Free for AI Pro/Ultra; enterprise via Code Assist | Shared harness with Antigravity 2.0 desktop; Skills/Hooks/Subagents |
| **Cursor CLI** | Cursor IDE users; long async runs | Auto-routes (Claude / GPT / Gemini) | Bundled with Cursor Pro ($20/mo) and above | Plan/Ask modes, Cloud Handoff with `&` prefix |
| **OpenCode** | Provider-agnostic, local models, scripting | Bring your own (75+ supported) | Free (open source, MIT) | 150K stars; LSP, SDK, dual build/plan agents |
`&`
## Summary
**What changed in 2026**:
**Top 5 CLI coding agents in 2026**:
`&`
**Honorable mentions**: [Aider](https://aider.chat) (still great for Git-native pair programming), [Warp 2.0](https://www.warp.dev/) (terminal-native ADE that runs Claude Code/Codex/Antigravity in one UI), [Sourcegraph Amp](https://sourcegraph.com/amp) (“Deep mode”), [OpenHands](https://github.com/All-Hands-AI/OpenHands), Goose, Qwen Code, Amazon Q Developer CLI, Crush, Plandex, Kimi CLI
**What to look for**: model choice (own API key vs subscription), local model support if privacy matters, sandboxed shell execution, MCP support, and how the agent handles long-running tasks (background, resumable)
### Why Use CLI Coding Agents and How to Choose the Right One
CLI agents are useful for a specific reason: they own the same surface your shell already owns. Files, processes, env vars, Git, `make`, `kubectl`, your project’s CLI - the agent can read and modify any of it without an IDE plugin in between. For long-running tasks (refactors, migrations, dependency bumps, “fix all the failing tests”), that’s a meaningful win over an IDE chat panel.
`make`
`kubectl`
The tradeoffs are real too. Most CLI agents trust the model to drive your shell, so a bad tool call can `rm -rf` something. Sandboxing varies a lot - Codex runs in a sandboxed env by default, Claude Code asks before destructive ops, Aider stays inside its file edit + commit lane. Read each tool’s default permission model before turning it loose on a real repo.
`rm -rf`
A rough decision tree for picking one:
### Top CLI Coding Agents in 2026
#### 1. Claude Code
Claude Code is Anthropic’s official CLI - `npm i -g @anthropic-ai/claude-code`, then `claude` in any repo. It’s the consensus “default” for serious work in 2026 and still tops most multi-file reasoning comparisons, especially after the Opus 4.7 update.
`npm i -g @anthropic-ai/claude-code`
`claude`
What it actually does well: it asks before destructive shell calls, keeps a coherent plan across long sessions (helped by the 200K context on Sonnet 4.6 and the larger Opus 4.7 window), and has the deepest plugin ecosystem - **Skills** (procedure libraries the agent loads on demand), **Subagents** (specialized child agents), **Hooks** (run on tool calls), and a growing list of MCP servers. The “Auto memory” feature added in 4.7 keeps user/feedback/project notes in `~/.claude/projects/.../memory/` so it doesn’t forget your conventions between sessions.
`~/.claude/projects/.../memory/`
Two real annoyances worth knowing: it’s cloud-only (no Ollama fallback), and at scale the API bill adds up fast - the Claude Pro/Max subscriptions ($20/$200/mo) bundle Claude Code quota, which is usually the better deal if you use it daily.
*[Content truncated...]*
---
## 5. bradAGI/awesome-cli-coding-agents - GitHub
**URL:** [https://github.com/bradagi/awesome-cli-coding-agents](https://github.com/bradagi/awesome-cli-coding-agents)
**Score:** 0.7109
### Summary
AgentDiff `⭐ 30` — Git-native provenance for AI-written code: hooks every CLI agent (Claude Code, Codex, Cursor, Gemini, OpenCode, Windsurf, Copilot) and records which agent wrote which line, reconciles it against each commit, and signs every attribution with ed25519. Records live in your own git refs (`agentdiff list/blame/report`); no server. Rust, MIT/Apache-2.0.
AgentManager `⭐ 27` — Lightweight CLI for managing multiple agent runs/sessions and workflows.
EchoCoding `⭐ 26` — Audio layer for CLI coding agents with hook-triggered SFX, ambient soundscape, and optional cloud TTS/ASR voice interaction for Codex and Claude Code workflows. [...] agent-deck `⭐ 441` — Terminal session manager for AI coding agents — one TUI for Claude, Gemini, OpenCode, Codex, and more. Worktree-aware, MCP integration, 8+ contributors. MIT.
ntm `⭐ 379` — Named Tmux Manager — spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette.
hcom `⭐ 370` — Hooks Claude Code, Antigravity, Codex, OpenCode, Kilo, and Cursor into a shared messaging and event bus; agents message, observe, and spawn each other mid-turn without changing how you use them. TUI dashboard, collision detection, cross-device relay. Rust, MIT. [...] Parallel Code `⭐ 818` — Desktop app for running multiple AI coding agents (Claude Code, Codex CLI, Gemini CLI) simultaneously in isolated git worktrees.
CLI Agent Orchestrator (CAO) `⭐ 797` — AWS's hierarchical multi-agent orchestration via tmux with intelligent task delegation patterns.
Agent Sessions `⭐ 688` — Local-first macOS session-history browser for AI coding agents, with transcript search across Codex, Claude Code, OpenCode, Cursor Agent, Hermes, Copilot CLI, OpenClaw, and more; resume is available where the underlying CLI supports it. MIT.
Catnip `⭐ 490` — Containerized environment + worktree automation for running multiple coding agents in parallel (optimized for Claude Code).
### Full Content
[Skip to content](#start-of-content)
## Navigation Menu
[Sign in](/login?return_to=https%3A%2F%2Fgithub.com%2Fbradagi%2Fawesome-cli-coding-agents)
Appearance settings
# Search code, repositories, users, issues, pull requests...
[Search syntax tips](https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax)
[Sign in](/login?return_to=https%3A%2F%2Fgithub.com%2Fbradagi%2Fawesome-cli-coding-agents)
[Sign up](/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=bradAGI%2Fawesome-cli-coding-agents)
Appearance settings
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert
{{ message }}
[bradAGI](/bradAGI) / **[awesome-cli-coding-agents](/bradAGI/awesome-cli-coding-agents)** Public
* [Notifications](/login?return_to=%2FbradAGI%2Fawesome-cli-coding-agents) You must be signed in to change notification settings
* [Fork 196](/login?return_to=%2FbradAGI%2Fawesome-cli-coding-agents)
* [Star 762](/login?return_to=%2FbradAGI%2Fawesome-cli-coding-agents)
# bradAGI/awesome-cli-coding-agents
[Branches](/bradAGI/awesome-cli-coding-agents/branches)[Tags](/bradAGI/awesome-cli-coding-agents/tags)
Open more actions menu
## Folders and files
| Name | Name | Last commit message | Last commit date |
| --- | --- | --- | --- |
| Latest commit History[112 Commits](/bradAGI/awesome-cli-coding-agents/commits/main/) 112 Commits |
| [.github/workflows](/bradAGI/awesome-cli-coding-agents/tree/main/.github/workflows "This path skips through empty directories") | [.github/workflows](/bradAGI/awesome-cli-coding-agents/tree/main/.github/workflows "This path skips through empty directories") | | |
| [scripts](/bradAGI/awesome-cli-coding-agents/tree/main/scripts "scripts") | [scripts](/bradAGI/awesome-cli-coding-agents/tree/main/scripts "scripts") | | |
| [README.md](/bradAGI/awesome-cli-coding-agents/blob/main/README.md "README.md") | [README.md](/bradAGI/awesome-cli-coding-agents/blob/main/README.md "README.md") | | |
| [banner.png](/bradAGI/awesome-cli-coding-agents/blob/main/banner.png "banner.png") | [banner.png](/bradAGI/awesome-cli-coding-agents/blob/main/banner.png "banner.png") | | |
| |
## Repository files navigation
# Awesome CLI Coding Agents
[](/bradAGI/awesome-cli-coding-agents/blob/main/banner.png)
[](https://awesome.re) [](https://github.com/bradAGI/awesome-cli-coding-agents/stargazers) [](#contributing) [](https://github.com/bradAGI/awesome-cli-coding-agents/blob/main/LICENSE)
A curated list of **90+ CLI coding agents** — AI-powered tools that live in your terminal, read/edit repos, and run commands — plus the **harnesses** that orchestrate, sandbox, or extend them.
> **Last updated:** 2026-07-06
### What is a CLI coding agent?
A CLI coding agent is an AI-powered tool that runs in your terminal and can autonomously read, write, and execute code in your repository. Unlike chat-based assistants, these agents have direct access to your filesystem, shell, and dev tools — they can edit files, run tests, commit changes, and iterate on errors. Think of them as AI pair programmers that live where you already work: the command line.
---
## Contents
* [Terminal-native coding agents](#terminal-native-coding-agents)
+ [Open Source](#open-source)
+ [OpenClaw ecosystem](#openclaw-ecosystem)
+ [Closed Source](#closed-source)
* [Harnesses & orchestration](#harnesses--orchestration)
+ [Session managers & parallel runners](#session-managers--parallel-runners)
+ [Orchestrators & autonomous loops](#orchestrators--autonomous-loops)
+ [Agent infrastructure](#agent-infrastructure)
* [Contributing](#contributing)
---
## Terminal-native coding agents
### Open Source
Forkable, extensible, and community-
*[Content truncated...]*
---