Search

latigo-engine — disciplined dev-harness for LLM/agentic development. Name reserved; active development, first public release upcoming.

latigo — disciplined dev-harness for LLM/agentic development. Name reserved; active development, first public release upcoming.

LangChain integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.

NexusCompute Unified SDK — renter, provider, storage P2P sync, pure-Python agent

Knowledge-driven multi-agent orchestration with LLM-powered query analysis and intelligent agent selection

Agentic coding terminal for the shell (runPixel gateway / OpenAI-compatible / offline backends)

A domain-agnostic orchestration engine for multi-agent desks: presence, a unified inbox, bounded meetings, and a wake ladder that proves delivery.

Guardrails for AI-agent tool/function calls: schema validation, realistic error recovery, cost/quota budgets, circuit breakers, and response caching. Framework-agnostic.

OpenRouter LLM benchmark for repair-agent and validator-agent model selection.

欣芸技术开发 Agent 流初始化包

Local security/audit layer for Claude Code: logs every tool call, blocks sensitive file access, generates session reports.

Parses agent harness session logs into a unified event schema. Under development.

ArchWright — the architecture auditor for AI agents

Python bindings for FlowgentraAI - build AI agents with graphs

Framework-agnostic evaluation, observability, and reliability for LLM agents.

Async multi-agent AI library for Python — self-improving agent loops, APEX synthesis, bounded agent spawning, multimodal input, and true token streaming across 100+ LLM providers.

Automate aim and item sales in Be A Lucky Block with this lightweight script.

An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.

RAG-агент по законам РФ: Telegram-бот с обязательной проверяемой цитатой статьи-источника. Командный дипломный проект; моя зона — слой бота (aiogram, FSM, форматтер, 152-ФЗ).

Agentic geopolitical simulation: LLM country-agents constrained by real data negotiate under a Game Master, with sourced hybrid RAG and an explainable risk engine.