Sandbox
73 repos for developer-tools · Codex · ResearchClear
AIDevGTM/
gtm-cofounder

#1 Product of The Day @ Product Hunt. The GTM co-founder you don't have. Open-source GTM Agent Skills for developer tools and AI products, for founders, GTM hires, and founding AEs: positioning, first users, launch, pricing. Sharpened by Frankl & Czakon. MIT.

273
PinkR1ver/
vibe-roast

Local-first AI coding personality profiler, usage dashboard, and evidence-grounded roast.

49

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

1.6k
ctxray/
ctxray

See how you really use AI — X-ray your AI coding sessions locally

46
tommy0103/
obelisk

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

473
vicarious11/
agenttop

htop for AI coding agents — monitor token usage, costs, and workflows across Claude Code, Cursor, Kiro, Codex, and Copilot

49
Klavis-AI/
klavis

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

5.8k
ctxrs/
ctx

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

1.1k
nablo-io/
lerim

Compiles AI agent traces and truns them into reusable context.

97

Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.

87
avivsinai/
langfuse-mcp

A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

105
jdrhyne/
agent-skills

A collection of AI agent skills for Clawdbot, Claude Code, Codex

241
Intina47/
context-sync

Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.

192

Agor - team command center for all things agentic

1.4k
rekal-dev/
rekal-cli

Your coding agent starts every session blank. Rekal is the memory your team is missing

193
nubbymong/
claude-command-center

Mission control for Claude Code: run many sessions in parallel with multi-account isolation, transcript viewer, cost tracking, and memory dashboards. Windows + macOS (Apple Silicon).

45
AIScientists-Dev/
Flowtrace

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

486
wquguru/
harness-books
wquguru/harness-booksTutorials & Guides

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

3.1k