#ai-agents

One CLI to manage AI agent configs from a single canonical store. One YAML source renders onto Claude Code, Codex, Copilot, OpenCode, Gemini and oh-my-pi: instructions, MCP servers, permissions and settings. Push to every agent, pull edits back, sync across machines via git.

Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.

A spec-driven coding harness. Process enforcement lives in a deterministic, local, tool-gated pipeline instead of an agent's context window.

CLI for 1Claw — secrets management for AI agents and humans

A bun-native UI development & testing system

TypeScript SDK for x402 buyers and sellers, with bounded Solana Tabs and one-shot multichain payments.

CLI for Goodeye: turn business outcomes into verified AI workflows that agents run reliably.

Universal memory provider for AI agents (Redis + Kumiho)

Genre-agnostic TypeScript game engine SDK — pure core plus React, Convex, WebSocket, Node host, and Postgres adapters

The definitive TypeScript library for SpaceMolt — WebSocket-v2-first, multi-account, with live local state caches. Internals regenerate from the server's OpenAPI spec.

No repository description published.

Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.

MCP server for persistent AI memory — give any AI assistant long-term recall. Works with Claude, Kiro, Cursor, Windsurf.

A web page annotation toolbar to help you better interact with AI coding agents.

Inspectable, source-traceable public-equity research for Codex, Claude Code, OpenCode, Grok Build and ChatGPT Work developer mode. 26 provisional method lenses, 34 MCP tools. Research software, not investment advice.

Decentralized networking protocol for AI agents — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.

agent memory progression system, like Beads but lighter/simpler

AI-powered triage for SAST findings.

Model-agnostic agent harness for Elixir

Self-Hosted API Management for Builders

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

Pi coding agent extension packages — tools, skills, and integrations.

Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes.

An agentic software factory that closes the loop

Stops Claude, Codex, and friends from stealing each other's Chrome tabs. Per-agent port + profile lanes. CLI + MCP server + live dashboard. Windows-first.

Memoria persistente para agentes de IA. Servidor MCP en Go, local-first y model-free.

Coordination ledger for coding agents: what was decided, what's still open, where you parked — durable across sessions, repos, and weeks. Memory tools store what the agent knows; Director tracks the state of the work. Run both: they don't overlap. Claude Code + Codex + OpenCode.

Search and retrieve US court opinions, federal dockets, judge records, citation networks, and oral arguments from CourtListener's 9M+ opinion corpus via MCP. STDIO or Streamable HTTP.

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

HTLC/PTLC deal-making for agents that meet in a chat room — offer, accept, lock, reveal, refund, as signed room messages. The room coordinates; a settlement rail holds the money. Alpha: no rail holds value yet.