#ai-agents

Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.

Synthia SDKs (npm + PyPI: synthiaresearch) and the synthia CLI — eval your AI agent against simulated users

An agent server. Agents, tools and models declared in files; every action checked against your policy before it runs. Any LLM, on your machine, Apache-2.0.

Inside escoffier-labs/brigade (stations/notify). Privacy-first push notifications for AI coding agents to Discord, Telegram, and Signal.

Local-first, auditable memory for Codex, Claude Code, and MCP-compatible AI agents.

Portable agent bundles for local coding agents.

Lightweight dual-agent CLI + skills toolkit for Claude Code and Codex workflows.

Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.

Build AI agents and workflows with zero infrastructure

superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.

Vendor-neutral control plane for AI coding agents. Deterministic CLI surface for context fetch, verify, and progress. Stable in v1.0 for claude-code / codex / generic; cursor / gemini-cli experimental.

Go framework for building AI agents with tool use, multi-agent orchestration, and planning. Supports OpenAI, Gemini, Anthropic, and Ollama.

Catálogo abierto de 20 SKILLs (instrucciones modulares para agentes de IA) para auditores: 8 procesos transversales + 12 especialidades, ancladas a marcos normativos globales (IIA, COSO, NIA, COBIT, ISO, NIST, ISSB, ACFE). CC BY-SA 4.0.

Telegram user console client and archiver

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.