Sandbox
2,808 repos for r · CodingClear

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

829

Project memory for coding agents and humans: the reasoning behind a codebase as Markdown in the repo, versioned by Git, so nothing rejected is proposed twice. No database, no daemon, no account.

155

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

1.6k
AIScientists-Dev/
Flowtrace

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

486

Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

4.3k
juyterman1000/
entroly

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

443
prime-radiant-inc/
iterative-development

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

179

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

40
Gabson0x/
bountyforge

All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.

410
shrek-abaper/
sap-engineering-skill

AI agent skills for SAP ABAP: ADT read/write CLI, 9-dimension code review, transport release gate, integration wiki. Works with Claude Code / opencode.

36
Cranot/
roam-code

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

517
jgravelle/
jdatamunch-mcp

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

81
NEWBIE0413/
gemini-gpt-hybrid

Multi-model orchestration subagents for Claude Code — delegates by task scope to Gemini's 1M-token context or GPT's fast iteration, then routes every result back through Claude review.

152

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

507
yetidevworks/
bosun

Tmux-native orchestrator for AI agent sessions. Rust + ratatui.

45
travis-rosser/
cofounder

Cofounder is a project harness that turns your AI coding agent into a technical cofounder.

1
1 add
flupkede/
codesearch

Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.

75
2389-research/
claude-plugins

28 plugins and MCP servers for Claude Code — TDD, multi-agent orchestration, iterative refinement, binary RE, structured decisions. Install any skill in one command.

95
ravitemer/
codecompanion-history.nvim

A history management extension for codecompanion AI chat plugin that enables saving, browsing and restoring chat sessions.

192
Aura-Technologies-llc/
ClaudeCodeMonitor

A lightweight macOS menu bar application that monitors and manages Claude Code instances in real-time. Keep track of multiple Claude sessions, their resource usage, and running processes - all from your menu bar.

44
img2threejs/
img2threejs

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

16k
sverklo/sverkloConnectors

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

79
sentrux/
sentrux

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

3.2k