Claude resources tagged “ open-source ”

Safety ✓ Privacy ✓by Tristan Tang · submitted by tristan666666

Agenta

Open-source prompt management, evaluation, and observability for LLM apps.

Safety ✓ Privacy ✓by Agenta · submitted by oktofeesh1

AgentOps

Open-source observability for AI agent traces, replays, and costs.

Safety ✓ Privacy ✓by AgentOps · submitted by oktofeesh1

Aider

Terminal AI coding assistant for Git repositories.

Safety · Privacy ✓by Aider

Archon

YAML workflow engine for deterministic, repeatable AI coding agent development.

Safety ✓ Privacy ✓by coleam00 · submitted by kiannidev

Asciinema

Record, replay, stream, and embed terminal sessions as text-based casts.

Safety ✓ Privacy ✓by asciinema · submitted by oktofeesh1

ast-grep

Fast AST-based structural search, linting, and rewriting for codebases.

Safety ✓ Privacy ✓by ast-grep · submitted by oktofeesh1

Browser Use

Open-source browser automation for AI agents.

Safety ✓ Privacy ✓by Browser Use

Continue

Open-source AI coding assistant with model control.

Safety · Privacy ✓by Continue

Daytona

Open-source sandbox infrastructure for executing AI-generated code in isolated environments, with SDKs, snapshots, and an optional managed cloud.

Safety ✓ Privacy ✓by Daytona · submitted by JPette1783

E2B

Open-source cloud sandboxes for executing AI-generated code, with Python and JavaScript SDKs and a Code Interpreter package.

Safety ✓ Privacy ✓by E2B · submitted by JPette1783

GitHub Community Issue Triage Agent

Triage GitHub issue queues with labels, issue types, milestones, duplicates, reproducibility checks, maintainer routing, and community-safe replies.

agents Review first External Review first

Safety ✓ Privacy ✓by MkDev11

Goose

Open-source, extensible AI agent that installs, executes, edits, and tests with any LLM, as a desktop app, CLI, and API.

Safety ✓ Privacy ✓by Agentic AI Foundation · submitted by JPette1783

Guardrails AI

Open-source input/output guardrails and validators for LLM apps.

Safety ✓ Privacy ✓by Guardrails AI · submitted by oktofeesh1

HumanLayer

Open-source IDE for orchestrating AI coding agents, built on Claude Code, with parallel sessions, worktrees, and team context engineering.

Safety ✓ Privacy ✓by HumanLayer · submitted by JPette1783

Instructor

Structured LLM outputs with Pydantic models, validation, and retries.

Safety ✓ Privacy ✓by 567 Labs · submitted by oktofeesh1

Label Studio

Open-source data labeling and human-in-the-loop AI evaluation.

Safety ✓ Privacy ✓by HumanSignal · submitted by oktofeesh1

Langfuse

Open-source LLM tracing and evaluation platform.

Safety · Privacy ✓by Langfuse

LiteLLM

Open-source AI gateway for routing LLM calls across providers.

Safety ✓ Privacy ✓by BerriAI · submitted by oktofeesh1

Microsoft PyRIT

Microsoft framework for generative AI risk identification and red-team assessment.

Safety ✓ Privacy ✓by Microsoft · submitted by oktofeesh1

mini-SWE-agent

Minimal CLI coding agent with confirm, human, and automatic execution modes.

Safety ✓ Privacy ✓by SWE-agent · submitted by oktofeesh1

NanoClaw

Open-source platform that runs Claude agents in isolated containers across messaging channels, with per-agent memory and vaulted credentials.

Safety ✓ Privacy ✓by nanocoai · submitted by JPette1783

Ollama

Local model runner for open models and developer workflows.

Safety ✓ Privacy ✓by Ollama · submitted by oktofeesh1

Open Source Evals Prompt Testing

Open-source evals bundle for prompt tests, RAG metrics, traces, human review, and regression gates.

Bundle:11 items

collections Review first External Review first

Safety ✓ Privacy ✓by MkDev11

Open Source PR Security Review Agent

Review public OSS PRs for trust-boundary, CI, secrets, dependency, provenance, and code-security risks before maintainer approval.

agents Review first External Review first

Safety ✓ Privacy ✓by MkDev11

Open SWE

Self-hosted coding agent framework built on LangGraph — trigger via Slack, Linear, or GitHub and get automatic PRs from isolated sandboxes.

Safety ✓ Privacy ✓by LangChain · submitted by JPette1783

OpenAI Codex CLI

OpenAI's open-source terminal coding agent that edits and runs code locally with sandbox and approval modes.

Safety ✓ Privacy ✓by OpenAI · submitted by JPette1783

OpenAI Evals

Build repeatable LLM and agent evals with OpenAI's open-source framework.

Safety ✓ Privacy ✓by OpenAI · submitted by JSONbored

OpenHands

Run coding agents with a local GUI, CLI, SDK, sandboxes, and hosted options.

rules Review first External Review first

Safety ✓ Privacy ✓by OpenHands · submitted by oktofeesh1

Production Codebase Auditor - CLAUDE.md Rules for Claude Code

Expert in comprehensive production codebase analysis with Zod validation enforcement, security vulnerability detection, and code consolid...

Added 10mo ago

Safety ✓ Privacy ✓by JSONbored

Pull Request Triage Capability Pack Skill

Triage maintainer PR queues with source-backed labels, reviewer routing, merge readiness checks, and privacy-safe queue summaries.

Level:expertType:capability-packVerified:validated

skills Review first Source-backed Review first

Safety ✓ Privacy ✓by kiannidev

Ragas

Open-source evaluation framework for RAG and LLM application testing.

Safety ✓ Privacy ✓by Vibrant Labs · submitted by oktofeesh1

Securing Agentic Coding Workflows In Open Source Repos

Secure open-source repos for Claude Code agentic workflows with MCP policy, permissions, review gates, and contributor safety practices.

guides Review first External Review first

Safety ✓ Privacy ✓by kiannidev

Serena MCP Server for Claude

Open-source MCP server that gives Claude semantic, symbol-level code retrieval and editing through language servers across many programming languages.

mcp Review first Source-backed Review first

Safety ✓ Privacy ✓by Oraios · submitted by glorydavid03023

Stagehand

AI-assisted browser automation framework.

Safety · Privacy ·by Browserbase

SuperClaude Framework

Open-source framework that extends Claude Code with slash commands, specialized agents, behavioral modes, and MCP integrations.