#ai-infrastructure (22 Repositories)
Ranked open-source repositories tagged with #ai-infrastructure, scored by pull request acceptance likelihood and maintainer engagement velocity.
64.7%
9.9h
22 repositories tagged #ai-infrastructure
SikamikanikoBG/homelab-monitor
Plug-and-play homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.
caura-ai/caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
matrixarkai/TemporalStore
Open-source Rust TemporalStore for LLM context management, temporal features, and risk control
Tencent-Hunyuan/UniRL
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
sandbaseai/sandbase-harness
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
ferro-labs/ai-gateway
Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.
tensorlakeai/tensorlake
Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications
jigjoy-ai/mozaik
Mozaik is a TypeScript runtime for building and sharing AI agents.
caura-ai/caura-memclaw
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
holon-run/holon
An agent workbench for ongoing work: preserve goals and progress, connect events and schedules, and resume when the next condition is met.
sandbaseai/managed-agents
Open-source CMA-compatible agent runtime. Run multi-agent systems locally with any model (Ollama/vLLM/Claude/GPT), MCP tools, scenario templates, and a beautiful dashboard. One command start. Built for enterprise teams.
HarnessRouter/harnessrouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
hanyeol/model-compose
Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.
reshaprio/reshapr
The open source, no-code MCP Server for AI-Native API Access
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
bojieli/ai-infra-book
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
ucsandman/DashClaw
Remote approvals, policy checks, and execution evidence for unattended AI agents.
tianyilt/qzcli_tool
启智平台任务管理 CLI：资源查询、任务提交、日志查看和 MCP/agent workflow
Paritok-official/paritok-4b-v1
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
CaviraOSS/LongMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
ai-infra-curriculum/ai-infra-engineer-learning
AI Infrastructure Engineer Learning Track - Production ML infrastructure curriculum (2-4 years experience)
RaycarlLei/tool-journal
TypeScript execution journal for retryable tools: SQLite durability, lease fencing, explicit uncertainty, and reproducible crash tests.