Search Results for "claude code" - Page 14
Sort By:
Showing 348 open source projects for "claude code"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
apra-fleet
Apra Fleet is an open-source MCP server
Apra Fleet is an open-source MCP server that pairs AI coding agents into doer-reviewer loops for higher quality code, and orchestrates them across machines via SSH when you need distributed power. Works with Claude Code, Gemini, Codex and other AI coding assistants. -
2
elephant
wanna continue claude session in codex?? use Elephant
Elephant is a context-preservation layer for AI coding agents that lets you switch between tools like Claude Code and Codex without losing the work already done. Instead of manually explaining a long conversation, repo structure, bug investigation, code changes, failed tests, and current objective every time an agent hits its usage limit or context window, Elephant continuously records the session while the agent is working. When you open the same repository with another agent, Elephant restores the important working state—what the previous agent was trying to achieve, what it discovered, which files it changed, what remains broken, and where to continue—so the new agent can pick up almost exactly where the previous one stopped. ... -
3
kapso
Long-running agents that optimize AI and Data systems
...Deliver a prediction model end to end, from data prep to a deployable artifact. Evolve the harness around a model: prompts, decoding, scoring. Set agents to improving agents until the metric climbs. Works with Claude Code and Codex. Proven in public: #1 open-source on MLE-Bench, #1 on ALE-Bench, ahead of the best tabular foundation model on RelBench, above every human at IOAI 2026. Docs: docs.leeroo.com/docs. Source: github.com/Leeroo-AI/kapso. -
4
Joanium Classic
Your smart, reliable, and friendly personal AI assistant.
Launch Of Joanium The AI era just shifted. Chatbots were phase one. Wrappers were phase two. Agents are phase three. Introducing Joanium — an open-source AI agent built for real execution. While others are still optimizing conversations, Joanium is built to plan, act, and deliver outcomes. Claude. OpenClaw. Hermes. They defined what came before. This is what comes next. Designed for a new standard: • Agent-first architecture (not chat-first) • Open source by... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
TypeUI
Design system skills for agentic tools
...TypeUI works seamlessly with popular AI coding environments like Claude, Codex, Cursor, and Gemini CLI. It also offers a registry of pre-built design styles that can be easily pulled into projects via simple CLI commands. Overall, TypeUI bridges the gap between AI-generated code and professional UI design by standardizing aesthetics across tools and workflows. -
6
TextSight AI Detector API Client
AI detector and AI humanizer API client for Python and JavaScript
Free, open-source Python and JavaScript client for the TextSight AI detector and AI humanizer API. Detect if text was written by ChatGPT, Claude or Gemini with a sentence-by-sentence AI score, and rewrite AI-sounding text so it reads naturally, in 3 lines of code. A developer-friendly alternative to the GPTZero, Originality.ai and ZeroGPT APIs. Zero dependencies, TypeScript types, automatic retries and a command line tool. Requires a TextSight API key. -
7
Maestro
Agent Orchestration Command Center
...Allowing for long-running unattended sessions, my current record is nearly 24 hours of continuous runtime. Run multiple agents in parallel with a Linear/Superhuman-level responsive interface. Currently supporting Claude Code, OpenAI Codex, and OpenCode with plans for additional agentic coding tools (Aider, Gemini CLI, Qwen3 Coder) based on user demand. -
8
GenRecipe
Publish vibe-first schemas that let anyone build working software
GenRecipe is the home for the Generative Recipe Methodology—a new way to create software by describing what you want and how it should feel, then letting AI build it. Instead of writing thousands of lines of code, you write a Generative Recipe: a structured, vibe-first schema that captures the intent, constraints, and emotional arc of an artifact. You feed this recipe to an AI (like Grok, Codex, or Claude), and it produces a working application in minutes. Why Generative Recipes? · Design is the Skill: You don't need to be a developer. ... -
9
Doberman-Core
Your AI's guard dog to stop it from going rogue.
...Built for developers and security teams, Doberman provides runtime policy enforcement, step-up authorization, audit logs and agent activity monitoring across tools like Claude Code, Codex, Cursor and other MCP-compatible systems. The open-source core is local-first and designed to act as a final security boundary when model-level guardrails fail. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
muse
AI agent memory system—pure Markdown, zero dependencies, fully local
MUSE gives AI coding agents persistent cross-session memory and multi-role governance through plain Markdown files. Supports Claude Code, OpenClaw, Cursor, Windsurf, Gemini CLI, and Codex via one-command install. Built-in MCP Server for programmatic access. 56 skills, auto memory capture, semantic compression, role-based governance, multi-project management. Pure Markdown, no database, no cloud. MIT open source. -
11
DevProjex
Turn any codebase into clean AI-ready context: GUI, TUI, CLI, MCP
DevProjex turns any folder or Git repository into clean, token-efficient context for AI assistants and coding agents, and shows exactly what leaves your machine before you send it. Use it as a desktop app (GUI), a keyboard-first terminal workspace (TUI), a scriptable CLI for CI, or a read-only MCP server for Claude Code, Cursor, and other agents. An open-source alternative to Repomix, gitingest, and code2prompt, with a visual file tree and live preview. Smart Ignore drops build output, dependencies, and caches based on real project evidence; Git modes pack only tracked, staged, changed, or diff files. Hide Secrets masks API keys, tokens, and passwords in every export; optional masking covers emails, IPs, and user paths. ... -
12
Council.
Open-source, serverless, multi-LLM group chat application
Council. is an open-source, serverless, multi-LLM group chat application designed to let you talk to multiple AI agents simultaneously. Have debates, get consensus, or collaborate with custom AI configurations. -
13
Orkas
Open-source local-first desktop AI workforce coordinated through chat.
...A Commander turns goals into executable plans and coordinates specialist agents in parallel or sequence through one chat. Orkas can coordinate built-in agents and external local agents such as Claude Code, Codex, OpenClaw, OpenCode, Hermes, and other supported runtimes. Conversations, files, agent configuration, and model keys stay local; the open-source edition uses user-selected providers or compatible local model endpoints. -
14
CodinIT.dev
Free, local, open-source AI app builder
...Deep Supabase integration means you can create UI and backend logic in one cohesive environment, while the model-agnostic architecture lets you connect to any AI, whether cloud-based (Gemini 3 Pro, GPT-5, Claude Sonnet 4.5) or local via Ollama, so you’re never locked in. All source code remains on your device and integrates seamlessly with your preferred IDE. A natural-language API enables powerful data queries and updates, automating tasks without leaving the chat interface. By running entirely locally, CodinIT.dev delivers maximum privacy, minimal latency, and smooth developer experiences free from cloud-based inconsistencies. -
15
Shinkai: Local AI Agents
Shinkai allows you to create advanced AI (local) agents effortlessly
Shinkai is a free, open-source AI platform that lets anyone create powerful AI agents without coding. These agents can collaborate with each other, handle complex tasks, and operate in decentralized crypto environments. Key Features: - No-Code Agent Creation - Build specialized agents (trading bots, sentiment trackers, etc.) with simple descriptions - Multi-Agent Collaboration - Agents work together to solve complex problems - Crypto Integration - Built-in support for decentralized payments and transactions - Flexible AI Models - Choose from cloud models (GPT-4, Claude) or run locally - Universal Compatibility - Works with Model Context Protocol (MCP) for cross-platform integration - Local Security - Crypto keys and computations stay on your device Shinkai transforms AI from single-task tools into collaborative, autonomous systems that can operate in decentralized networks while maintaining privacy and security. -
16
nim_duilib
Cross-platform C++ desktop UI framework with XML-driven skins and Skia
...) - Skia rendering, windowless controls, CPU/GPU acceleration - Images: SVG/PNG/GIF/JPG/BMP/APNG/WEBP/ICO; Animations: GIF/APNG/WEBP/Lottie/PAG - Dynamic skins, light/dark themes, accent colors - Window shadows, DPI awareness, runtime multi-language switching - CEF (109/142) and WebView2 integration; SDL3 windowing - 22 examples; AI-assisted dev skills for Claude Code and TRAE Compilers: VS2022/2026, VS2017/2019 (C++17 branch), LLVM, MinGW-W64, gcc, clang. One-click scripts build Skia and all dependencies. License: MIT. Source: https://github.com/rhett-lee/nim_duilib -
17
Prompt Engineering Interactive Tutorial
Anthropic's Interactive Prompt Engineering Tutorial
Prompt-eng-interactive-tutorial is a comprehensive, hands-on tutorial that teaches the craft of prompt engineering with Claude through guided, executable lessons. It starts with the anatomy of a good prompt and moves into techniques that deliver the “80/20” gains—separating instructions from data, specifying schemas, and setting evaluation criteria. The course leans heavily on realistic failure modes (ambiguity, hallucination, brittle instructions) and shows how to iteratively debug prompts the way you would debug code. -
18
Bot on Anything
Large model-based chatbot builder that can quickly integrate AI models
Bot on Anything is a versatile open-source AI chatbot builder that lets developers connect large language models such as ChatGPT, Claude, and Gemini to virtually any messaging platform, website, or interface with minimal configuration. At its heart, the project abstracts away the glue logic between AI model APIs and disparate application “channels,” enabling the same bot logic to run in Slack, Telegram, Gmail, enterprise tools, web UIs, or command-line terminals. -
19
TPLS
High Resolution Direct Numerical Simulation (DNS) of Two-Phase Flows
...We also provide a simplified version of the code 'S-TPLS' to help new users understand the code structure and algorithms. The next step will be to include a model of boiling. -
20
Qwable-v1
Agentic coding model combining Opus reasoning and Fable tools
Qwable-v1 is an open-weight agentic coding model created through a chained distillation process based on Qwen3.6-35B-A3B. The model combines two distinct training stages: first, it was fine-tuned on reasoning traces derived from Claude Opus 4.7 to improve structured reasoning, and then further trained on Claude Fable-5 agentic tool-use traces to develop autonomous coding and tool-calling behavior. The result is a 35B Mixture-of-Experts model with only 3B active parameters that can switch between deep reasoning and agent-style execution depending on the system prompt. ... -
21
Postproxy-MCP
MCP (Model Context Protocol) server for integrating PostProxy API
PostProxy MCP is a Model Context Protocol (MCP) server that integrates the PostProxy API directly into Claude Code, enabling AI-assisted publishing to social media platforms like Instagram, YouTube, TikTok, Facebook, LinkedIn, X/Twitter, and Threads. -
22
i1n
Localization as code. One command to translate your app
...Review and edit translations in the dashboard, mark them as manually approved, and get notified when source text changes make translations stale. Ships with an MCP server that connects to AI coding assistants (Cursor, Claude Code, Windsurf) so your agent can internationalize components directly from the IDE. Bridge Mode wraps existing i18next or next-intl setups with type safety, no migration needed. Open source CLI (MIT). Free tier is permanent. -
23
lastest
AI-supported visual verification and tests you can actually trust.
Lastest.cloud is a free, open-source verification of development, self-hosted visual regression and end-to-end testing platform for web applications. An AI agent records you clicking through your running app and generates Playwright tests with multi-selector fallback. Replays are deterministic and token-free, so your CI/CD bill doesn't scale with your test suite. Lastest ships three diff engines side-by-side — pixel (pixelmatch), structural (SSIM), and perceptual (Butteraugli) — so...
