Coding agents

qwen-audio-agent

QwenAudio/qwen-audio-agent

Huia Project Score 79

qwen-audio-agent is a realtime voice runtime that sits in front of a coding or task agent. You talk to a voice model, longer jobs go to a backend agent while the conversation continues, and when a task finishes its result comes back into the same conversation. The voice side is swappable. Cloud options listed in the README include Qwen Audio 3.0 Realtime, GPT-Live / OpenAI Realtime, Google Gemini Live and Doubao Seeduplex 3.0 Realtime, each needing that provider's API key. Hugging Face Speech-to-Speech and MiniCPM-o 4.5 can run locally. Backend agents connect mostly over ACP: the list covers Qwen Code, OpenCode, OpenClaw and Kimi Code, with Codex and Claude Code joining through an external ACP adapter. You can use it from a WebUI, a terminal TUI or a desktop floating orb on macOS, Windows and Linux. The README also lists parallel background tasks you can query or cancel, cross-session memory, and scheduled reminders. The package is published on npm under Apache-2.0, a technical report is on arXiv, and the repository sits in the QwenAudio GitHub organization.

Stars

2.9K

Language

JavaScript

License

Apache-2.0

Momentum

Emerging

ponytail

DietrichGebert/ponytail

Huia Project Score 76

Ponytail is a rule set and skill collection that pushes an AI coding agent to write as little code as a task needs. It ships as a plugin for Claude Code, Codex, GitHub Copilot CLI, Gemini CLI and several other agent hosts, and as plain rules files for editors such as Cursor, Windsurf and Cline. Before writing anything, the agent works down a fixed ladder: drop the feature if it does not need to exist, reuse what the codebase already has, then try the standard library, a native platform feature, an installed dependency and a one-line answer. New code comes only after all of those fail. The README is firm that validation, error handling, security and accessibility are off limits for cutting. Its example: asked for a date picker, the agent reaches for a native <input type="date"> instead of adding a library and a wrapper component. The plugin adds commands to set the intensity (lite, full, ultra or off), to review a diff or a whole repository for over-engineering, and to collect deferred shortcuts into a ledger. The maintainer publishes a benchmark: across twelve feature tasks on a FastAPI and React template with Haiku 4.5, the README reports about 54% fewer lines of code than the same agent without the skill, plus smaller drops in tokens, cost and time.

Stars

162K

Language

JavaScript

License

MIT

Momentum

+5.7% 7dEstablished

agent-skills

addyosmani/agent-skills

Huia Project Score 75

Agent Skills is a repository of 25 Markdown workflows for AI coding agents, covering software work from specification and planning through testing, review, performance, security, deployment and documentation. Each skill is a SKILL.md process with triggers, steps, red flags, verification criteria and common rationalizations to counter. The pack can be installed with the skills CLI or integrated with tools including Claude Code, Cursor, Gemini CLI, OpenCode, GitHub Copilot and Codex. Nine slash commands map development tasks to skills. /build auto can generate a plan and implement its tasks after one approval, while stopping on failures or risky steps. This suits teams that want an agent to follow a defined engineering process instead of relying on isolated prompts. The repository also contains four review personas, shared checklists, evaluation cases and host-specific adapters. One installation limitation matters: installing a single skill through npx does not copy the repository-level references/ directory, so links to shared checklists are unavailable unless those files are supplied another way.

Stars

106K

Language

JavaScript

License

MIT

Momentum

+4.9% 7dEstablished

orca

stablyai/orca

Huia Project Score 74

Orca is a desktop development environment for running multiple AI coding agents side by side, with each task isolated in its own Git worktree. It can launch agents such as Claude Code, Codex, Cursor CLI and OpenCode, while keeping terminals, files, diffs and browser sessions tied to each worktree. The project is aimed at developers who already use coding-agent command-line tools and want one place to manage several sessions. Orca runs on macOS, Windows and Linux. Worktrees can run locally, on SSH machines or on a remote Orca server that you control. Its built-in browser includes a Design Mode that can send an element's HTML, CSS and screenshot to an agent. The CLI can create worktrees, control terminals, open files and diffs, and automate Orca's browser. A mobile companion for iOS and Android can monitor sessions, send replies, inspect files and source control, and receive completion notifications. Orca does not provide an AI model or hosted compute. You bring the coding-agent accounts or subscriptions you already use, and remote execution uses machines or cloud accounts under your control.

Stars

91K

Language

TypeScript

License

MIT

Momentum

+7.8% 7dEstablished

ECC

affaan-m/ECC

Huia Project Score 73

ECC is an open-source system that adds reusable engineering workflows, skills, agents, memory, rules, hooks and security checks to coding agents. Its main path is Claude Code, with guided installation also available for Codex and Kimi Code. The repository also contains adapters for other coding agents, but the project warns that support is not equal across them. The current repository includes 68 agents, 293 skills and 94 legacy command shims. The supplied workflows cover tasks such as planning, testing, implementation, review, build repair, security and architecture. ECC also includes AgentShield integration for scanning agent configuration, prompts, hooks, MCP settings, permissions, secrets and related files. Hooks and memory can enforce checks outside the prompt, store session information and support its continuous-learning system. The easiest starting point is the ecc-universal guided installer. Claude Code setup needs Node.js 18 or newer, Git and Claude Code 2.1 or newer on PATH. The multi-agent installer can configure Claude Code, Codex and Kimi Code in one reviewed flow. Kimi installation is more limited: ECC writes managed project files but does not configure Kimi hooks, model or provider settings, or authentication.

Stars

278K

Language

JavaScript

License

MIT

Momentum

+2.2% 7dEstablished

graphify

Graphify-Labs/graphify

Huia Project Score 72

Graphify turns a software project and related material into a queryable knowledge graph. It parses code locally with tree-sitter, connects structures such as calls, imports and inheritance, and writes the result to graph.json. It can also produce an interactive graph.html viewer and a GRAPHREPORT.md report. Queries can search the graph, explain a concept or trace a path between concepts. Code analysis does not require an LLM or API key. Graphify distinguishes relationships extracted directly from source from relationships resolved by Graphify. It does not use embeddings or a vector store for its graph. Documents, PDFs and images can join the same graph, but their semantic processing uses an AI assistant or configured model backend rather than the code-only parser. The project also supplies a skill that can be registered with supported coding assistants including Claude Code, Cursor, Codex and Gemini CLI.

Stars

126K

Language

Python

License

Apache-2.0

Momentum

+2.0% 7dEstablished

caveman

JuliusBrussee/caveman

Huia Project Score 72

Caveman is a skill plus a local proxy that reduce the tokens a coding agent spends, both in what it writes back and in what it reads. The skill changes the reply style: answer first, one idea per sentence, no greeting or recap. Code, commands, file paths, error messages and numbers are kept character for character, and your own prompts are never rewritten. There are three levels (/caveman, /ultracave and /megacave, the last one in classical Chinese) and extra commands for one-line commit messages, terse code review and shrinking memory files such as CLAUDE.md. The second part is the caveman CLI, which runs on your machine and compresses bulky input before the agent sees it: logs, CSV, YAML, JSON and test output. Originals stay on disk so the agent can pull them back. The CLI also has caveman browse for compact web pages and caveman learn, which ranks where tokens went in past sessions. Separate TypeScript and Python middleware packages apply the same compression to agents built on the Vercel AI SDK, LangChain, OpenAI or Anthropic calls. The project's own benchmark reports 33.2% fewer input tokens over 54 Claude Code runs, with 18 of 18 answers correct. The same table shows HTML sessions getting 9.9% worse, because HTML has no compressor yet.

Stars

111K

Language

Go

License

Apache-2.0

Momentum

+1.6% 7dEstablished

codebase-memory-mcp

DeusData/codebase-memory-mcp

Huia Project Score 71

codebase-memory-mcp is an MCP server, written in C, that parses a code repository into a knowledge graph so an AI coding agent can ask structural questions (what calls this function, which HTTP routes exist, what a change affects) instead of reading files one by one. It ships as one native executable for macOS, Linux and Windows. Parsing uses tree-sitter grammars compiled into the binary, and the README lists 162 languages. A hybrid LSP layer adds type resolution for a smaller set, including Python, TypeScript, Go, Java and Rust. Agents reach the graph through 17 MCP tools covering search, call tracing, architecture overviews, change detection, Cypher queries and architecture decision records. A 3D graph viewer is built into the binary and opens at localhost:9749. The installer finds supported agents on your machine and writes their MCP configuration; the README counts 45 client surfaces, among them Claude Code, Codex, Gemini CLI, Cursor and Windsurf. The authors describe the design in an arXiv preprint and report 83% answer quality with 10 times fewer tokens than file-by-file exploration across 31 repositories. Indexing and queries run locally without an API key.

Stars

46K

Language

C

License

MIT

Momentum

+1.6% 7dEstablished

ui-ux-pro-max-skill

nextlevelbuilder/ui-ux-pro-max-skill

Huia Project Score 71

UI UX Pro Max is an agent skill that hands coding assistants a searchable library of design guidance, so a request such as a landing page for a spa comes back with a matching style, color palette, font pairing and page structure. It installs into Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, Gemini CLI, Kiro and about a dozen more assistants, through the Claude Code plugin marketplace or the uipro command from the ui-ux-pro-max-cli npm package. Under the hood it is a set of CSV datasets and a Python search script that ranks entries with BM25. The README counts 79 searchable UI styles (50 active), 192 palettes tied to 192 product types, 74 font pairings, 25 chart types, 119 UX guidelines and advice for 22 stacks, from React and Next.js to SwiftUI, Flutter and WPF. Version 2.0 added a design system generator that merges those searches into one recommendation, with anti-patterns to avoid and a pre-delivery checklist covering contrast, focus states and reduced motion. You can save the result as a master file with per-page overrides that the agent reads in later sessions. In most supported assistants the skill switches on by itself for UI requests. Kiro, Copilot, Roo Code and KiloCode use the /ui-ux-pro-max slash command instead. A paid premium edition with brand and asset features is sold separately on uupm.cc.

Stars

135K

Language

Python

License

MIT

Momentum

+1.9% 7dEstablished

headroom

headroomlabs-ai/headroom

Huia Project Score 71

Headroom is a Python and TypeScript tool that shrinks the text an AI agent sends to a model (tool output, logs, files, RAG chunks and chat history) so each request uses fewer tokens. The compression runs on your own machine. You can use it in four ways: a compress() library for Python and TypeScript, a local proxy you point an app at, a headroom wrap command that starts coding agents such as Claude Code, Codex or Aider through that proxy, or an MCP server. A router looks at each piece of content and picks a compressor: one for JSON, one for source code, and a small Hugging Face model called Kompress-v2-base for prose. Originals stay in a local cache, and the model can call a retrieve tool when the short version is not enough. The project publishes its own offline benchmark of four MCP-style scenarios, with savings from 21% to 57%. The README also describes steering the model toward shorter replies and labels that saving as an estimate. The latest release is v0.39.1, from September 2026.

Stars

75K

Language

Python

License

Apache-2.0

Momentum

+1.1% 7dEstablished

rtk

rtk-ai/rtk

Huia Project Score 70

RTK (Rust Token Killer) is a command-line proxy that trims the terminal output of common developer commands before an AI coding agent reads it, so less of the agent's context fills up with noise. It ships as one Rust binary. When an agent runs something like git status, a hook installed by rtk init swaps it for rtk git status, which returns a compact version: failing tests only, grouped lint errors, one-line git confirmations, shortened directory trees. The README lists filters for git, the GitHub CLI, test runners such as pytest, Jest and cargo test, linters, package managers, Docker, kubectl, AWS and Pulumi, and claims more than 100 supported commands with under 10 ms of added time. When a command fails, RTK keeps the full unfiltered output so the agent can fetch it with rtk recall instead of running the command again. The project is careful about its own numbers. It says it cuts up to 90% of the bash output an agent reads, and states plainly that this does not mean a 90% smaller bill, since shell output is only part of the input tokens. Token counts in rtk gain are estimated as bytes divided by four because RTK has no tokenizer.

Stars

83K

Language

Rust

License

Apache-2.0

Momentum

+1.0% 7dEstablished

TencentDB-Agent-Memory

TencentCloud/TencentDB-Agent-Memory

Huia Project Score 69

TencentDB Agent Memory is a self-hosted memory service from Tencent Cloud that stores what AI agents learn and shares it across agents and team members. It turns past work into four kinds of memory asset. Chat Memory keeps preferences, facts and decisions, distilled from raw conversation through layers named L0 Conversation, L1 Atom, L2 Scenario and L3 Persona. Skills capture reusable procedures with versions and validation rules. LLM-Wiki builds linked pages from documents, and CodeGraph indexes symbols, files and call relationships so an agent can check what a change might affect. A web panel called Memory Hub tracks ownership, versions and access, with private, team and ACL-based visibility. Agents connect through a proxy. You point the agent's base URL at it, and the README says no plugin, hook or MCP server is needed. Listed clients include Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes and OpenClaw. Setup starts three services (memory-core, memory-hub and proxy) with Docker and a start script, and asks for two sets of LLM settings. The README reports a PersonaMem score of 76% with the system against 48% without it, which is the project's own figure. Team Memory is labeled beta.

Stars

28K

Language

TypeScript

Momentum

Established

Understand-Anything

Egonex-AI/Understand-Anything

Huia Project Score 68

Understand Anything turns a codebase or supported knowledge base into an interactive knowledge graph for exploring files, functions, classes, dependencies, and relationships. Its code analysis combines Tree-sitter structural parsing with LLM-generated summaries, tags, architectural layers, tours, and business-domain information. The dashboard lets you search the graph, inspect nodes, follow relationships, and view code organized by architectural layer. The main /understand workflow creates .ua/knowledge-graph.json, with older projects continuing to use .understand-anything/. Later runs are incremental by default and re-analyze changed files. Separate commands cover change-impact analysis, explanations of specific code, onboarding guides, domain graphs, and Karpathy-pattern wiki analysis. The project supports Claude Code and a range of other coding agents and IDE integrations. Generated graph data can be committed to a repository and opened by teammates with the standalone viewer. That viewer needs Node.js 18 or newer and reads the graph from local disk without LLM calls. Building or running the analysis code from source requires Node.js 22 or newer and pnpm 10 or newer.

Stars

86K

Language

TypeScript

License

MIT

Momentum

+1.1% 7dEstablished

oh-my-openagent

code-yeongyu/oh-my-openagent

Huia Project Score 66

OmO (the repository is oh-my-openagent) is a terminal agent for coding and other work, started with a single omo command. It runs on senpi, the author's fork of the pi coding agent, with extra features built in. You open a project, run omo and describe the job. Adding the keyword ultrawork (or ulw) to a prompt tells the agent to read the codebase first, plan, check each step and verify the result before it stops. Typing mass ulw splits a large job into a graph of agents that run in parallel, each on a model picked for its part. A memory feature called Kibitzer keeps notes as markdown files in a git repository and has a cheaper model warn the main agent before it repeats an earlier mistake. The /login command signs in with Claude, ChatGPT, Kimi and GLM subscriptions. OmO installs as a native binary through a shell script (PowerShell on Windows) or as the omo-ai package from npm or Bun. People on the older OpenCode edition can carry their settings over with omo setup. GitHub lists the licence as "Other"; the repository's LICENSE.md is the Sustainable Use License.

Stars

70K

Language

TypeScript

Momentum

+0.3% 7dEstablished

deepseek-harness

deepseek-ai/deepseek-harness

Huia Project Score 65

DeepSeek Harness is an open-source agent runtime from DeepSeek AI that runs coding agents through a Web UI, headless jobs, SDK connections or ACP automation clients. Its Cordis-based design treats the model adapter, tools, session log and agent loop as plugins, so these parts can be replaced or extended through configuration. The Web UI works with a selected project directory. An agent can read and edit files, execute commands, delegate work and keep a plan, subject to the configured approval policy. The default setup supports DeepSeek models, while the model settings also support shipped third-party providers and custom APIs using OpenAI Chat Completions, OpenAI Responses or Anthropic Messages protocols. Developers can add their own Harness plugins, including plugins that register tools or services. The project is currently an experimental developer preview. Its maintainers warn that compatibility-breaking changes will occur and that it has not received a security audit. Because agents can execute generated commands and access permitted files, processes, credentials and networks, the safety documentation recommends restricted privileges and isolated environments.

Stars

249K

Language

TypeScript

License

MIT

Momentum

+2.3% 7dEmerging

A macOS workspace for running and reviewing multiple coding agents side by side.

Self-hosted server that runs pi coding-agent sessions in isolated remote sandboxes you can reach from a terminal or phone.

An AI code editor and coding agent that plans, writes and reviews code on your desktop, in the terminal, in Slack and in the cloud.

Anthropic's coding agent that reads a codebase, edits files and runs commands from the terminal, IDE, desktop app or web.

GitHub's AI coding assistant for code completion, chat, agent mode, code review and cloud agents across editors, the CLI and GitHub.

Cognition's AI code editor, formerly Windsurf, for running and reviewing local and cloud coding agents from one app.

A test runbook for web and mobile apps: an AI assistant drafts the plan, and testers or agents record results over MCP.

Desktop development environment that runs several AI coding agents in parallel, one ticket and one Git worktree each.

Answer Claude Code permission prompts, questions and plan reviews from a Wear OS watch or an Android phone.

Mac app that shows what AI coding agents do in Xcode: live sessions, build timelines, errors and test results in one window.

Watches production logs, metrics and traces, investigates issues and opens pull requests with fixes for your team to review.

A Mac app that shows Claude Code, Codex and other coding agents as status dots and lets you answer them from one Inbox.

Video reference library that turns launch films and explainers into blueprints and prompt recipes Claude and other agents can build from.

Practices for polars data processing with dataframely: Schema and Collection definitions, .validate() and .filter(), type hints and testing.

Claude Code, Codex, GitHub Copilot·★ 618·checked Oct 12, 2026

A Python reference covering syntax, concurrency, networking, databases, ML/LLM work and HPC, for Python questions, interview prep, debugging and development.

Claude Code·★ 8.2K·checked Oct 12, 2026

Knowledge and Python utilities for making animated GIFs optimized for Slack, covering size constraints, validation tools and animation concepts.

Claude Code, Claude.ai, Claude API·★ 181K·checked Oct 12, 2026

Builds complex, multi-component claude.ai HTML artifacts with React, Tailwind CSS and shadcn/ui, for work needing state, routing or shadcn/ui components rather than single-file artifacts.

Claude Code, Claude.ai, Claude API·★ 180K·checked Oct 4, 2026

Audits and rewrites text to remove AI writing patterns, with a detect-only mode, an edit-in-place mode for files, optional voice profiles and an iterate-to-convergence pass.

Claude Code, Cursor, VS Code Copilot·★ 4.8K·checked Oct 4, 2026

For any task where a spreadsheet file is the main input or output: reading, editing, fixing, creating, cleaning or converting .xlsx, .xlsm, .xltx, .csv or .tsv files.

Claude Code·★ 180K·checked Oct 4, 2026

A toolkit for testing local web applications with Playwright: checking frontend behavior, debugging the UI, taking browser screenshots and reading browser logs.

Claude Code·★ 180K·checked Oct 4, 2026

Creates new agent skills, edits and improves existing ones, runs evals and benchmarks on them, and tunes a skill's description so it triggers more reliably.

Claude Code, Claude.ai, Cowork·★ 180K·checked Oct 4, 2026

Used whenever a .pptx or .potx file is involved: creating decks, reading or extracting text, editing presentations, combining or splitting slides, and working with templates, layouts, notes or comments.

Claude Code, Claude.ai, Claude API·★ 180K·checked Oct 4, 2026

Handles PDF tasks: reading and extracting text or tables, merging, splitting, rotating, watermarking, creating, filling forms, encrypting or decrypting, extracting images and OCR on scanned files.

Claude Code, Claude.ai, Claude API·★ 180K·checked Oct 4, 2026

Guides an agent toward distinctive, deliberate visual design when building or reworking a UI, covering aesthetic direction, typography and choices that avoid templated defaults.

Claude Code, Claude.ai, Claude API·★ 180K·checked Oct 4, 2026

Applies Anthropic's brand colors and typography to artifacts that should carry Anthropic's look, when brand colors, style guides or company design standards matter.

Claude Code, Claude.ai, Claude API·★ 180K·checked Oct 4, 2026