Search

TestDog is a desktop test case management tool: generate UI test scripts from natural language or manual recording, then replay them as-written with Playwright to verify (everyday regression costs no model tokens). Built for end-to-end regression testing of web applications.

FSM syntactic engine to repair truncated/broken JSON from LLMs (streaming, Pydantic, zero-regex core)

Local multi-agent coordination protocol for terminal coding agents

A local AI coding-agent workbench and runtime with lightweight terminal collaboration and structured task workflows.

One-shot execution skill for GitHub Copilot

A persistent agent team for long-running collaboration in DeepSeek Harness

No One's Memory Management — persistent, self-updating knowledge-graph memory for LLM apps

LangChain integration for Anlyon state primitives and trace callbacks

Unofficial, rclone-backed CLI for Mail.ru Cloud

Switch auth profiles for AI coding agents while keeping app config and history shared.

LayerX Network is a deterministic execution and accounting network for autonomous agents.

MemGuard - eBPF-based real-time memory poisoning detection and alerting for LLM agents (AgentSight overlay)

rio_ai: a ported multi-provider LLM streaming SDK. rio_agent: a SKILL.state long-horizon agent runtime (arXiv:2608.26263). rio_coding: a SKILL.state coding agent.

Point vLLM (or any OpenAI-client-based consumer) at Algenta's own OpenAI-compatible /v1/chat/completions and /v1/responses surface -- a thin base-url/api-key helper plus a real, honest capability-fidelity conformance suite

Experimental n8n root node for an OpenAI Responses Agent, currently validating binary-aware AI tool execution.

Enterprise-grade, markdown-native SDLC Multi-Agent Framework with Autonomous Brain Mapping, Low-Input High-Output workflows, and universal AI agent compatibility.

agentguard for tool calls that bypass MCP: wrap OpenAI Agents SDK, LangChain or plain function tools with the same policy engine (spend caps, approvals, kill switch, dry-run, loop breaker, audit log) and cap LLM spend with a guarded fetch.

Shared fingerprinting and storage primitives for the agentbelt suite.

The Itera Learning local agent: capture hooks, the spool, the installer and the shipper. Captures your coding-agent work and ships it to the Itera Learning engine.

Conversational Intent Firewall for AI agents. Screen WhatsApp, Telegram, and chat messages for prompt injection, social engineering, and fraud in <10ms.