See where a Copilot CLI or pi coding-agent session spent its time, tokens and credits, and what to change.
Write code from specifications.
See where a Copilot CLI or pi coding-agent session spent its time, tokens and credits, and what to change.
CLI tool to download AXIOM coding agent setup files into your project
Local encrypted credential vault for coding agents — secrets never touch agent context, only the process boundary
HADES — Universal AI Agent CLI Runtime
Install Seatbelt MCP + /seatbelt skill (npx withseatbelt)
Self-contained MCP server that turns any website into a runnable MCP server, in-process. Host-as-brain by default (no API key); optional OpenAI/Anthropic/Gemini/Groq/Ollama/... or a custom inference URL.
MCP (Model Context Protocol) Server for TypeScript Type Guard Generation - Generate runtime validation functions from TypeScript types
Model Context Protocol (MCP) server for Cerebras Code API integration with any MCP-compatible client. Run 'cerebras-mcp --config' for setup or 'cerebras-mcp --remove' for cleanup.
Point at any UI element in your running app and leave a note for your coding agent.
Single source of truth for AI coding agent configuration (Cursor, Claude Code, Cline, Codex, Windsurf, Continue.dev)
MCP server that gives AI agents LightningChart JS source-of-truth guidance.
Local MCP server that lets your coding agent read visual-feedback comments pinned to web pages with the Pinback Chrome extension.
Is your AI agent capping? nocap runs the receipt and finds out if its 'done' claim is true — a lie detector for AI coding agents. Receipts over self-report.
Project-aware, evidence-driven operating system, multi-agent CLI, and secure MCP desktop bridge for coding agents.
P31 Vibe Coding MCP Server — generate and deploy apps via MCP tools for neurodivergent families
Bst-Table MCP server — gives AI coding agents accurate, version-pinned knowledge of @bloomskill/table-* : docs search, the feature-toggle registry, cell types, config validation and grid scaffolding.
Stop AI coding agents from cheating your checks. Diff-aware guard that catches deleted or skipped tests, weakened assertions, @ts-ignore, test-runner detection, lowered coverage and disabled CI steps, with a Claude Code hook that blocks the agent until it
The complete collection of OpenCode coding agent configs: agents, skills, hooks, commands, rules, and Graphify code intelligence.
Minimal surface, complete architecture: a small, local-first coding-agent harness re-derived from the invariants of DeepSeek Harness (independent project; not affiliated).
Coordinate parallel coding agents, above Git