| 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:** 2026-06-22 00:05:39
---
## 1. The Ultimate Guide to AI Coding Assistants for Modern Developers – FarFeshplus
**URL:** [https://farfeshplus.pro/the-ultimate-guide-to-ai-coding-assistants-for-modern-developers](https://farfeshplus.pro/the-ultimate-guide-to-ai-coding-assistants-for-modern-developers)
**Score:** 0.8316
### Summary
In 2026 tools like GitHub Copilot, Cursor, Claude Code, Windsurf, Amazon Q Developer, OpenAI Codex, Tabnine and Gemini Code Assist have become part of everyday development work. Many teams now use AI during planning coding testing debugging documentation and code reviews.
Recent reports also show that AI-generated code activity has grown rapidly across platforms like GitHub. Developers are producing more code than ever before and many teams are shipping projects faster without increasing team size. [...] ## Conclusion
AI coding assistants have evolved far beyond simple autocomplete tools. Platforms such as GitHub Copilot, Cursor, Claude Code, Windsurf and OpenAI Codex now help with everything from code generation and debugging to large-scale refactoring and project analysis.
The biggest lesson for developers is that there isn’t one perfect assistant for every situation. Copilot works extremely well inside established workflows. Cursor excels at AI-native development and project-wide changes. Claude Code stands out when deeper reasoning and system understanding are needed.
The developers getting the most value from these tools aren’t the ones handing over complete control. They’re the ones combining AI speed with human judgment. [...] Every one of these tools focuses on a slightly different workflow.
GitHub Copilot remains popular among enterprise teams because it integrates naturally into existing development environments. Cursor has become known for understanding entire codebases and handling changes across multiple files. Claude Code is often chosen when developers need deeper reasoning or help understanding large systems. Windsurf has gained attention among developers looking for an AI-first coding experience at a more affordable price.
### Matching the Tool to the Job
One mistake many developers make is searching for a single tool that does everything.
Experienced engineers usually take a different approach. They often combine multiple tools depending on the task.
### Full Content
[FarFeshplus](https://farfeshplus.pro/)
# The Ultimate Guide to AI Coding Assistants for Modern Developers
Software development has changed more in the last few years than it did during most of the previous decade. A big reason for that change is the rise of AI coding tools.
Not long ago these tools were mainly used for simple autocomplete suggestions. Today they’re capable of understanding entire projects writing tests explaining unfamiliar code suggesting improvements and even handling tasks that involve multiple files. Because of that developers spend less time doing repetitive work and more time solving real problems.
In 2026 tools like [GitHub Copilot](https://github.com/features/copilot), [Cursor](https://cursor.com), [Claude Code](https://www.anthropic.com/claude-code), [Windsurf](https://windsurf.com), [Amazon Q Developer](https://aws.amazon.com/q/developer/), [OpenAI Codex](https://openai.com/codex), [Tabnine](https://www.tabnine.com) and [Gemini Code Assist](https://cloud.google.com/products/gemini/code-assist) have become part of everyday development work. Many teams now use AI during planning coding testing debugging documentation and code reviews.
Recent reports also show that AI-generated code activity has grown rapidly across platforms like [GitHub](https://github.com). Developers are producing more code than ever before and many teams are shipping projects faster without increasing team size.
This guide isn’t about convincing anyone to use AI. Most developers have already experimented with these tools. The real goal here is to understand how modern coding assistants work where they genuinely help what risks they create and how developers can use them without sacrificing code quality or engineering judgment.
## Choosing the Right AI Coding Assistant in 2026
The AI coding assistant market is packed with options right now. New tools appear regularly and every platform claims to be faster smarter or more capable than the competition.
Even with all those choices most products fall into two main categories.
The first category includes coding assistants. These tools help developers write code faster by generating suggestions completing functions and handling repetitive programming tasks.
The second category includes coding agents. These systems can take on larger responsibilities with less supervision. Instead of helping with individual pieces of code they can work through complete tasks and coordinate changes across multiple files.
Understanding the difference matters because different developers need different levels of automation. A freelancer working on small projects may want one type of tool while a large engineering team may need something entirely different.
### Understanding Today’s Major Platforms
Several products dominate conversations among software developers today:
Every one of these tools focuses on a slightly different workflow.
GitHub Copilot remains popular among enterprise teams because it integrates naturally into existing development environments. Cursor has become known for understanding entire codebases and handling changes across multiple files. Claude Code is often chosen when developers need deeper reasoning or help understanding large systems. Windsurf has gained attention among developers looking for an AI-first coding experience at a more affordable price.
### Matching the Tool to the Job
One mistake many developers make is searching for a single tool that does everything.
Experienced engineers usually take a different approach. They often combine multiple tools depending on the task.
For example a frontend developer may use Cursor for interface development Copilot for day-to-day coding support and Claude Code when working through major refactoring projects.
That’s why choosing an AI assistant is less about finding the perfect brand and more about building the workflow that fits the way you work. Different tools shine in different situations and understanding those strengths is usually more valuable than chasing the latest trend.
## How AI Coding Assistants Actually Work
**Score:** 0.7767
### Summary
What changed in 2026: GitHub now has 4.7 million paid subscribers (75% YoY growth) according to Microsoft earnings reports. Agent Mode launched in February 2026 with multi-agent workflows across Copilot, Claude, and Codex agents. The Copilot CLI reached GA with autonomous coding capabilities. Copilot Memory (public preview) automatically deduces and stores repository information. Claude Sonnet 4 is the default model for the Copilot CLI and a primary model in VS Code's automatic model selection for paid users.
Pricing (pre-June 2026):
| Plan | Price | Premium Requests |
---
| Free | $0/mo | 50/month |
| Pro | $10/user/mo | 300/month |
| Pro+ | $39/user/mo | 1,500/month |
| Business | $19/user/mo | 300/user/month |
| Enterprise | $39/user/mo | 1,000/user/month | [...] What changed in 2026:Cursor 2.0 launched with a proprietary Composer model (described as "4x faster than similarly intelligent models") and a multi-agent interface supporting up to eight parallel agents. A February 2026 update then further expanded agent capabilities: background agents can now run in parallel on their own isolated VMs, test their own changes, and record their work via video, logs, and screenshots. Cursor also launched Bugbot for automated PR review ($40/user/month add-on). Revenue reached $2B+ ARR by March 2026 per TechCrunch.
Pricing: Cursor moved to usage-based pricing in June 2025. [...] Headcount tradeoffs at 50/200/500 developers. At 50 developers, the primary constraint is team velocity: you want each engineer shipping more without increasing review burden. At 200, the constraint shifts to architectural consistency: can every engineer make changes that respect system boundaries they did not build? At 500, the constraint is organizational knowledge loss: can your AI tool onboard and upskill faster than attrition degrades institutional expertise? Tools like Cursor and Claude Code optimize for individual velocity at the 50-developer scale. Augment Code's Context Engine and the new Cosmos platform address the 200-500 developer problem: architectural reasoning, shared memory across agents, and specialized experts that compound organizational knowledge rather than letting it
### Full Content
# 8 Best AI Coding Assistants [Updated May 2026] | Augment Code
[Skip to content](https://www.augmentcode.com/tools/8-top-ai-coding-assistants-and-their-best-use-cases#main-content)
[](https://www.augmentcode.com/)
Product
Solutions
[Context Engine](https://www.augmentcode.com/context-engine)[Pricing](https://www.augmentcode.com/pricing)[Docs](https://docs.augmentcode.com/)[Blog](https://www.augmentcode.com/blog)
Resources
[Sign in](https://cosmos.augmentcode.com/)[Book demo](https://www.augmentcode.com/contact)
Product
[Cosmos](https://www.augmentcode.com/#meet-cosmos)[CLI](https://www.augmentcode.com/product/cli)[Changelog](https://www.augmentcode.com/changelog)
Solutions
[Code Review Review every PR with agents](https://www.augmentcode.com/solutions/code-review)[Test Coverage Coverage that climbs, suites that stay green](https://www.augmentcode.com/solutions/test-coverage)[Incident Management Investigate alerts before humans arrive](https://www.augmentcode.com/solutions/incident-management)[Ticket to PR Assign a ticket, merge a reviewed PR](https://www.augmentcode.com/solutions/ticket-to-pr)[Large Projects From design doc to shipped feature](https://www.augmentcode.com/solutions/large-projects)[Automations Recurring work as repeatable workflows](https://www.augmentcode.com/solutions/automations)[Security Remediation From CVE alert to a reviewed fix](https://www.augmentcode.com/solutions/security-remediation)[Migrations Modernization as a program, not a project](https://www.augmentcode.com/solutions/migrations)[Onboarding Ramp every engineer in days](https://www.augmentcode.com/solutions/onboarding)[Team Standards at Scale Your best workflow, everyone's default](https://www.augmentcode.com/solutions/standardization)
[Context Engine](https://www.augmentcode.com/context-engine)[Pricing](https://www.augmentcode.com/pricing)[Docs](https://docs.augmentcode.com/)[Blog](https://www.augmentcode.com/blog)Resources
[Customers](https://www.augmentcode.com/customers)[Careers](https://www.augmentcode.com/careers)[Status Page](https://status.augmentcode.com/)[Trust Center](https://trust.augmentcode.com/)[Security](https://www.augmentcode.com/security)
[Talk to Sales](https://www.augmentcode.com/contact)[Sign in](https://cosmos.augmentcode.com/)
[](https://www.augmentcode.com/)[Book demo](https://www.augmentcode.com/contact)
[Back to Tools](https://www.augmentcode.com/tools)
# 8 Best AI Coding Assistants [Updated May 2026]
Jan 14, 2026 Last updated: Jun 17, 2026•
Molisha Shah
![Image 3: 8 Best AI Coding Assistants [Updated May 2026]](https://cdn.sanity.io/images/oraw2u2c/production/c3d0c7a1e18eb3dfcbc36967162f53123aaa20af-1600x900.svg)
The best AI coding assistant for enterprise teams managing complex distributed codebases is Augment Code, because its Context Engine provides deep semantic codebase indexing, its Auggie CLI achieved a 51.80% score on SWE-bench Pro, the top result at the time of publication, and it provides architectural reasoning that helps prevent cross-service production incidents.
## TL;DR
Evaluating AI coding assistants for large, messy codebases is difficult because enterprise teams need architectural understanding, not just fast autocomplete. Many tools now offer autonomous agents, yet [only 29% of developers trust AI accuracy](https://stackoverflow.blog/2026/02/18/closing-the-developer-ai-trust-gap/) according to Stack Overflow's 2025 Developer Survey, which means speed alone does not solve the real problem. This ranking compares eight assistants across architectural reasoning, multi-file accuracy, security posture, speed to correct answer and cost predictability. The conclusions come from 40+ hours of testing on a 450K-file monorepo, where Augment Code delivered the deepest cross-service understanding, Cursor offered the fastest prototyping velocity, and GitHub Copilot provided the lowest-friction adoption path.
### Context Engine maps dependencies across your entire monolith in minutes, not weeks.
[Get started](https://www.augmentcode.com/install?utm_source=growthx&utm_medium=listicle&utm_campaign=content-cta&utm_content=cta1)
Free tier available · VS Code extension · Takes 2 minutes
If you're a CTO or VP Eng already spending seven figures on AI tokens, the real question is not "which tool autocompletes fastest" but "which of these gets us real ROI on our existing AI spend, and what are the disqualifying criteria for our codebase?" This ranking is built around that question.
## What Changed in the AI Coding Landscape Since 2025
The AI coding assistant market underwent a significant transformation between mid-2025 and early 2026. If you evaluated tools even six mon
*[Content truncated...]*
---
## 3. 11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price ...
**URL:** [https://www.morphllm.com/ai-coding-agent](https://www.morphllm.com/ai-coding-agent)
**Score:** 0.7373
### Summary
### About How we train and deploy models.### Careers Join a small team shipping daily.
Book a Call
Sign Up / Log In
Home/11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price, License
# 11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price, License
Codex CLI tops Terminal-Bench 2.1 at 83.4%, Claude Code with Opus 4.8 at 78.9%. OpenCode (176k stars, MIT) is the most-starred open source agent. Full ranked table: scores, exact prices, license.
June 18, 2026·1 min read
Which Coding Agent Is BestTerminal-Bench 2.1 LeaderboardPricing, Side by SideClaude CodeOpenAI Codex CLICursorGitHub CopilotOpenCodeClineAiderGemini CLI and AntigravityGoose, Kilo Code, KiroCline vs OpenCodeKilo Code vs OpenCodeAider vs OpenCodeOpen Source Model BackendFAQ [...] | Rank | Agent + model | Terminal-Bench 2.1 | SWE-bench Pro | Entry price | License / stars |
--- --- --- |
| 1 | Codex CLI + GPT-5.5 | 83.4% | n/a | ChatGPT Plus $20/mo | Apache-2.0, 92,003 |
| 2 | Claude Code + Opus 4.8 | 78.9% | 69.2% | Pro $17/mo annual | Proprietary, 131,380 |
| 3 | Gemini CLI + Gemini 3.1 Pro | 70.7% | n/a | Free (1,000 req/day) | Apache-2.0, 105,395 |
| 4 | Cursor (Composer 2.5) | n/a | n/a | Hobby $0; Pro $20/mo | Proprietary IDE |
| 5 | GitHub Copilot | n/a | n/a | Free $0; Pro $10/mo | Proprietary |
| 6 | OpenCode (BYOK) | n/a | n/a | Free | MIT, 176,017 |
| 7 | Cline (BYOK) | n/a | n/a | Free | Apache-2.0, 63,501 |
| 8 | Aider (BYOK) | n/a | n/a | Free | Apache-2.0, 46,434 |
| 9 | Kilo Code (BYOK) | n/a | n/a | Free | MIT, 19,968 | [...] #### GitHub Copilot moved to credit billing on June 1, 2026
Copilot replaced premium request units with GitHub AI Credits (1 credit = $0.01). Pro $10/mo = 1,500 credits ($15 value), Pro+ $39/mo = 7,000 credits ($70), the new Max $100/mo = 20,000 credits ($200). Basic code completions never consume credits and stay unlimited on paid plans. Note: as of June 2026, new sign-ups for Copilot Student, Pro, Pro+, and Max are paused while the billing change rolls out.
## Claude Code
Best for reasoning depth on hard problems, in the terminal.
### Full Content
# 11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price, License
[Morph](https://www.morphllm.com/)
Models
Specialized
### [Fast Apply Merge AI-generated code edits instantly.](https://www.morphllm.com/products/fastapply)### [WarpGrep AI search subagent with sub-6s searches.](https://www.morphllm.com/products/warpgrep)### [Compact Verbatim context compaction for long-running agents.](https://www.morphllm.com/products/compact)### [Model Router Auto-route each prompt to the best model.](https://docs.morphllm.com/sdk/components/router)
Open Source Models
### [DeepSeek 1M-context model, served fast.](https://www.morphllm.com/products/models)### [MiniMax 230B MoE for agentic workflows.](https://www.morphllm.com/products/models)### [Qwen 397B MoE, 262k context.](https://www.morphllm.com/products/models)
### [SDK](https://docs.morphllm.com/sdk)
### [Glance](https://www.morphllm.com/products/glance)
[Docs](https://docs.morphllm.com/quickstart)[Pricing](https://www.morphllm.com/pricing)[MCP](https://www.morphllm.com/setup)
Resources
### [Blog Engineering deep dives and product updates.](https://www.morphllm.com/blog)### [Startup Credits Up to $5K in API credits for startups.](https://www.morphllm.com/startups)### [Students Free for a year with student verification.](https://www.morphllm.com/students)### [Contact Us Talk to the team about your use case.](https://www.morphllm.com/contact)
### [About How we train and deploy models.](https://www.morphllm.com/about)### [Careers Join a small team shipping daily.](https://www.ycombinator.com/companies/morph/jobs/)
[Book a Call](https://calendar.app.google/xN2RcfSYtfQERQYG8)
[Sign Up / Log In](https://www.morphllm.com/sign-up)
[Home](https://www.morphllm.com/)/11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price, License
# 11 AI Coding Agents Ranked (2026): Terminal-Bench Scores, Price, License
Codex CLI tops Terminal-Bench 2.1 at 83.4%, Claude Code with Opus 4.8 at 78.9%. OpenCode (176k stars, MIT) is the most-starred open source agent. Full ranked table: scores, exact prices, license.
June 18, 2026·1 min read
[Which Coding Agent Is Best](https://www.morphllm.com/ai-coding-agent#ranking)[Terminal-Bench 2.1 Leaderboard](https://www.morphllm.com/ai-coding-agent#terminal-bench)[Pricing, Side by Side](https://www.morphllm.com/ai-coding-agent#pricing)[Claude Code](https://www.morphllm.com/ai-coding-agent#claude-code)[OpenAI Codex CLI](https://www.morphllm.com/ai-coding-agent#codex-cli)[Cursor](https://www.morphllm.com/ai-coding-agent#cursor)[GitHub Copilot](https://www.morphllm.com/ai-coding-agent#copilot)[OpenCode](https://www.morphllm.com/ai-coding-agent#opencode)[Cline](https://www.morphllm.com/ai-coding-agent#cline)[Aider](https://www.morphllm.com/ai-coding-agent#aider)[Gemini CLI and Antigravity](https://www.morphllm.com/ai-coding-agent#google)[Goose, Kilo Code, Kiro](https://www.morphllm.com/ai-coding-agent#others)[Cline vs OpenCode](https://www.morphllm.com/ai-coding-agent#cline-vs-opencode)[Kilo Code vs OpenCode](https://www.morphllm.com/ai-coding-agent#kilo-vs-opencode)[Aider vs OpenCode](https://www.morphllm.com/ai-coding-agent#aider-vs-opencode)[Open Source Model Backend](https://www.morphllm.com/ai-coding-agent#model-backend)[FAQ](https://www.morphllm.com/ai-coding-agent#faq)
On the public Terminal-Bench 2.1 leaderboard, Codex CLI with GPT-5.5 is #1 at 83.4% and Claude Code with Opus 4.8 is #2 at 78.9%. For open source, OpenCode (176,017 stars, MIT) is the most-starred agent, ahead of Gemini CLI (105k) and OpenAI Codex (92k). The best pick depends on whether you weight benchmark ceiling, cost, or running your own model. The full ranked table of 11 agents, with prices, install commands, and scores verified June 18, 2026, is below.
#### Best AI coding agent by goal
Verified June 18, 2026. Scores from Terminal-Bench 2.1 (tbench.ai), prices from vendor pages.
Highest benchmark
Codex CLI + GPT-5.5
83.4% Terminal-Bench 2.1, #1
Deepest reasoning
Claude Code + Opus 4.8
78.9% Terminal-Bench, 69.2% SWE-bench Pro
Most open source
OpenCode (MIT)
176,017 stars, 75-plus providers
Free, model-agnostic: OpenCode, Cline, Aider, Kilo Code, Gemini CLI (60 req/min, 1,000/day free).Best IDE flow: Cursor (Pro $20/mo).Cheapest paid default: GitHub Copilot Pro ($10/mo).
## Terminal-Bench 2.1 leaderboard (the agent benchmark that matters)
Terminal-Bench measures an agent driving a real terminal to complete development tasks: editing files, running commands, fixing failures. It tests the agent and model together, which is the right unit, because the same model scores differently inside different agents. Scores below are from the public [tbench.ai leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.1) as of June 18, 2026.
#### Terminal-Bench 2.1 (agent + model)
Percentage of terminal development tasks completed. Higher is better.
1 Codex CLI + GPT-5.5#1 83.4%
2 Claude
*[Content truncated...]*
---
## 4. GitHub - safishamsi/graphify: AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. · GitHub
**URL:** [https://github.com/safishamsi/graphify](https://github.com/safishamsi/graphify)
**Score:** 0.7341
### Summary
graphify claude uninstall
graphify codebuddy install # CODEBUDDY.md + PreToolUse hook (CodeBuddy)
graphify codebuddy uninstall
graphify codex install # AGENTS.md + PreToolUse hook in .codex/hooks.json (Codex)
graphify opencode install # AGENTS.md + tool.execute.before plugin (OpenCode)
graphify kilo install # native Kilo skill + /graphify command + AGENTS.md + .kilo plugin
graphify kilo uninstall
graphify cursor install # .cursor/rules/graphify.mdc (Cursor)
graphify cursor uninstall
graphify gemini install # GEMINI.md + BeforeTool hook (Gemini CLI)
graphify gemini uninstall
graphify copilot install # skill file (GitHub Copilot CLI)
graphify copilot uninstall
graphify aider install # AGENTS.md (Aider) [...] Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. CodeBuddy uses the same Agent tool and PreToolUse hook mechanism as Claude Code. Factory Droid uses the `Task` tool for parallel subagent dispatch. OpenClaw and Aider use sequential extraction (parallel agent support is still early on those platforms). Trae uses the Agent tool for parallel subagent dispatch and does not support PreToolUse hooks — AGENTS.md is the always-on mechanism.
> Codex uses `$graphify` instead of `/graphify`.
### Optional extras [...] | `graphify install` |
| Claude Code (Windows) | `graphify install` (auto-detected) or `graphify install --platform windows` |
| CodeBuddy | `graphify install --platform codebuddy` |
| Codex | `graphify install --platform codex` |
| OpenCode | `graphify install --platform opencode` |
| Kilo Code | `graphify install --platform kilo` |
| GitHub Copilot CLI | `graphify install --platform copilot` |
| VS Code Copilot Chat | `graphify vscode install` |
| Aider | `graphify install --platform aider` |
| OpenClaw | `graphify install --platform claw` |
| Factory Droid | `graphify install --platform droid` |
| Trae | `graphify install --platform trae` |
| Trae CN | `graphify install --platform trae-cn` |
| Gemini CLI | `graphify install --platform gemini` |
### Full Content
# GitHub - safishamsi/graphify: AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. · GitHub
[Skip to content](https://github.com/safishamsi/graphify#start-of-content)
## Navigation Menu
Toggle navigation
[](https://github.com/)
[Sign in](https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fsafishamsi%2Fgraphify)
Appearance settings
*
Platform
*
AI CODE CREATION
* [GitHub Copilot Write better code with AI](https://github.com/features/copilot)
* [GitHub Copilot app Direct agents from issue to merge](https://github.com/features/ai/github-app)
* [MCP Registry New Integrate external tools](https://github.com/mcp)
*
DEVELOPER WORKFLOWS
* [Actions Automate any workflow](https://github.com/features/actions)
* [Codespaces Instant dev environments](https://github.com/features/codespaces)
* [Issues Plan and track work](https://github.com/features/issues)
* [Code Review Manage code changes](https://github.com/features/code-review)
*
APPLICATION SECURITY
* [GitHub Advanced Security Find and fix vulnerabilities](https://github.com/security/advanced-security)
* [Code security Secure your code as you build](https://github.com/security/advanced-security/code-security)
* [Secret protection Stop leaks before they start](https://github.com/security/advanced-security/secret-protection)
*
EXPLORE
* [Why GitHub](https://github.com/why-github)
* [Documentation](https://docs.github.com/)
* [Blog](https://github.blog/)
* [Changelog](https://github.blog/changelog)
* [Marketplace](https://github.com/marketplace)
[View all features](https://github.com/features)
*
Solutions
*
BY COMPANY SIZE
* [Enterprises](https://github.com/enterprise)
* [Small and medium teams](https://github.com/team)
* [Startups](https://github.com/enterprise/startups)
* [Nonprofits](https://github.com/solutions/industry/nonprofits)
*
BY USE CASE
* [App Modernization](https://github.com/solutions/use-case/app-modernization)
* [DevSecOps](https://github.com/solutions/use-case/devsecops)
* [DevOps](https://github.com/solutions/use-case/devops)
* [CI/CD](https://github.com/solutions/use-case/ci-cd)
* [View all use cases](https://github.com/solutions/use-case)
*
BY INDUSTRY
* [Healthcare](https://github.com/solutions/industry/healthcare)
* [Financial services](https://github.com/solutions/industry/financial-services)
* [Manufacturing](https://github.com/solutions/industry/manufacturing)
* [Government](https://github.com/solutions/industry/government)
* [View all industries](https://github.com/solutions/industry)
[View all solutions](https://github.com/solutions)
*
Resources
*
EXPLORE BY TOPIC
* [AI](https://github.com/resources/articles?topic=ai)
* [Software Development](https://github.com/resources/articles?topic=software-development)
* [DevOps](https://github.com/resources/articles?topic=devops)
* [Security](https://github.com/resources/articles?topic=security)
* [View all topics](https://github.com/resources/articles)
*
EXPLORE BY TYPE
* [Customer stories](https://github.com/customer-stories)
* [Events & webinars](https://github.com/resources/events)
* [Ebooks & reports](https://github.com/resources/whitepapers)
* [Business insights](https://github.com/solutions/executive-insights)
* [GitHub Skills](https://skills.github.com/)
*
SUPPORT & SERVICES
* [Documentation](https://docs.github.com/)
* [Customer support](https://support.github.com/)
* [Community forum](https://github.com/orgs/community/discussions)
* [Trust center](https://github.com/trust-center)
* [Partners](https://github.com/partners)
[View all resources](https://github.com/resources)
*
Open Source
*
COMMUNITY
* [GitHub Sponsors Fund open source developers](https://github.com/sponsors)
*
PROGRAMS
* [Security Lab](https://securitylab.github.com/)
* [Maintainer Community](https://maintainers.github.com/)
* [Accelerator](https://github.com/accelerator)
* [GitHub Stars](https://stars.github.com/)
* [Archive Program](https://archiveprogram.github.com/)
*
REPOSITORIES
* [Topics](https://github.com/topics)
* [Trending](https://github.com/trending)
* [Collections](https://github.com/collections)
*
Enterprise
*
ENTERPRISE SOLUT
*[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:** 0.7258
### Summary
`⭐ 33`
AgentDiff `⭐ 29` — 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.
`⭐ 29`
`agentdiff list/blame/report`
AgentManager `⭐ 26` — Lightweight CLI for managing multiple agent runs/sessions and workflows.
`⭐ 26`
codex-profiles `⭐ 26` — Bash CLI helper for switching OpenAI Codex CLI/Desktop accounts via isolated `CODEX_HOME` profiles; Homebrew install with `brew install Ducksss/tap/codex-profile`. MIT, no token copying.
`⭐ 26`
`CODEX_HOME`
`brew install Ducksss/tap/codex-profile` [...] `⭐ 727`
CLI Agent Orchestrator (CAO) `⭐ 708` — AWS's hierarchical multi-agent orchestration via tmux with intelligent task delegation patterns.
`⭐ 708`
Agent Sessions `⭐ 642` — 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.
`⭐ 642`
Catnip `⭐ 486` — Containerized environment + worktree automation for running multiple coding agents in parallel (optimized for Claude Code).
`⭐ 486`
ntm `⭐ 353` — Named Tmux Manager — spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette.
`⭐ 353` [...] `⭐ 74`
OpenCastle `⭐ 49` — Multi-agent orchestration framework that turns AI coding assistants (Copilot, Cursor, Claude Code, OpenCode, Windsurf, Codex CLI) into 19 coordinated specialist agents. CLI-driven (`npx opencastle init`), with task decomposition, parallel work, and quality gates. MIT.
`⭐ 49`
`npx opencastle init`
great\_cto `⭐ 40` — Engineering-management layer of 34 specialist AI agents covering the full SDLC (architect, PM, senior-dev, reviewer, QA, security, devops, L3-support + 18 archetype-specific reviewers) with auto-detected archetypes and compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Runs in Claude Code, Cursor, Codex CLI, Aider, and Continue via AGENTS.md + MCP. MIT.
`⭐ 40`
### Full Content
## Navigation Menu
# Search code, repositories, users, issues, pull requests...
# Provide feedback
We read every piece of feedback, and take your input very seriously.
# Saved searches
## Use saved searches to filter your results more quickly
To see all available qualifiers, see our [documentation](https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax).
# bradAGI/awesome-cli-coding-agents
## Folders and files
| Name | | Name | Last commit message | Last commit date |
| --- | --- | --- | --- | --- |
| Latest commit History[107 Commits](/bradAGI/awesome-cli-coding-agents/commits/main/) 107 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") | | |
| View all files | | |
## Latest commit
## History
## 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:** 2026-06-17
### 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)
[Harnesses & orchestration](#harnesses--orchestration)
[Contributing](#contributing)
## Terminal-native coding agents
### Open Source
Forkable, extensible, and community-driven. Sorted by GitHub stars. Provider tags `[Company]` indicate the backing organization.
`[Company]`
**[Hermes Agent](https://github.com/NousResearch/hermes-agent)** `⭐ 194k` — Nous Research's self-improving CLI agent with persistent memory, aut
*[Content truncated...]*
---