#Ai-infrastructure

Showing 44 of 44 repositories tagged #ai-infrastructure, ranked by stars

airweave-ai
airweave-ai
airweave

Open-source context retrieval layer for AI agents

Score
100
โ˜… 6.5k โ‘‚ 814 +5/day
Python
CaviraOSS
CaviraOSS
OpenMemory

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Score
100
โ˜… 4.3k โ‘‚ 489 +13/day
TypeScript
open-compress
open-compress
claw-compactor

14-stage Fusion Pipeline for LLM token compression โ€” reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

Score
100
โ˜… 2.2k โ‘‚ 209 +5/day
Python
ai-infra-curriculum
ai-infra-curriculum
ai-infra-engineer-learning

AI Infrastructure Engineer Learning Track - Production ML infrastructure curriculum (2-4 years experience)

Score
100
โ˜… 1.4k โ‘‚ 239 +38/day
Python
semantica-agi
semantica-agi
semantica

Semantica ๐Ÿง  โ€ข Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI.

Score
0
โ˜… 1.4k โ‘‚ 200 +1/day
Python
ucsandman
ucsandman
DashClaw

๐Ÿ›ก๏ธThe governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.

Score
86
โ˜… 284 โ‘‚ 50 +4/day
TypeScript
abraxas914
abraxas914
VESTI

Local-first AI conversation memory hub to capture, search, summarize, and export chats across major AI platforms. ๆœฌๅœฐไผ˜ๅ…ˆ็š„ AI ๅฏน่ฏ่ฎฐๅฟ†ไธŽ็Ÿฅ่ฏ†ไธญๅฐใ€‚

Score
89
โ˜… 278 โ‘‚ 12 +1/day
TypeScript
divagr18
divagr18
memlayer

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

Score
71
โ˜… 278 โ‘‚ 32 +1/day
Python
caura-ai
caura-ai
caura-memclaw

Governed shared memory for AI agent fleets โ€” multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Score
95
โ˜… 278 โ‘‚ 34 +19/day
Python
Corpus-OS
Corpus-OS
corpusos

Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.

Score
79
โ˜… 223 โ‘‚ 7 โ€”
Python
TonyStef
TonyStef
Grov

Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.

Score
29
โ˜… 191 โ‘‚ 12 โ€”
TypeScript
ai-infra-curriculum
ai-infra-curriculum
ai-infra-junior-engineer-learning

AI Infrastructure Junior Engineer Learning Track - Comprehensive curriculum for entry-level ML infrastructure engineers (0-2 years experience)

Score
86
โ˜… 183 โ‘‚ 37 +8/day
Python
ferro-labs
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.

Score
84
โ˜… 173 โ‘‚ 30 +8/day
Go
SikamikanikoBG
SikamikanikoBG
homelab-monitor

Plug-and-play homelab dashboard in one container โ€” GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.

Score
71
โ˜… 146 โ‘‚ 22 +4/day
Python
holon-run
holon-run
holon

A local workbench for agents doing continuous work across sessions, commands, human input, and external events.

Score
57
โ˜… 132 โ‘‚ 12 +1/day
Rust
reshaprio
reshaprio
reshapr

The open source, no-code MCP Server for AI-Native API Access

Score
43
โ˜… 107 โ‘‚ 20 โ€”
Java
tianyilt
tianyilt
qzcli_tool

ๅฏๆ™บๅนณๅฐไปปๅŠก็ฎก็† CLI๏ผš่ต„ๆบๆŸฅ่ฏขใ€ไปปๅŠกๆไบคใ€ๆ—ฅๅฟ—ๆŸฅ็œ‹ๅ’Œ MCP/agent workflow

Score
50
โ˜… 103 โ‘‚ 28 +3/day
Python
pmady
pmady
keda-gpu-scaler

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Score
57
โ˜… 102 โ‘‚ 32 +27/day
Go
redevops-io
redevops-io
sidekick

Local coding-agent orchestrator โ€” DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.

Score
0
โ˜… 100 โ‘‚ 0 โ€”
Python
greynewell
greynewell
infermux

Route inference across providers.

Score
100
โ˜… 94 โ‘‚ 7 โ€”
Go
redevops-io
redevops-io
context-runtime

Context Runtime โ€” a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.

Score
50
โ˜… 87 โ‘‚ 0 โ€”
Python
redbco
redbco
redb-open

Distributed data mesh for real-time access, migration, and replication across diverse databases โ€” built for AI, security, and scale.

Score
0
โ˜… 80 โ‘‚ 7 โ€”
Go
k8s-lynq
k8s-lynq
lynq

โš“๏ธ Kubernetes-Native Database-Driven Provisioning Workflow Automation

Score
29
โ˜… 78 โ‘‚ 6 โ€”
Go
hanyeol
hanyeol
model-compose

Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.

Score
68
โ˜… 75 โ‘‚ 3 โ€”
Python
Papr-ai
Papr-ai
memory-opensource

Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval

Score
53
โ˜… 73 โ‘‚ 5 +2/day
Python
sinaptik-ai
sinaptik-ai
starpod

Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-extending skills, cron, and multi-channel support.

Score
58
โ˜… 72 โ‘‚ 10 โ€”
Rust
latenceainew
latenceainew
vllm-factory

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

Score
74
โ˜… 71 โ‘‚ 7 +1/day
Python
Battam1111
Battam1111
Myco

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.

Score
14
โ˜… 64 โ‘‚ 7 +1/day
Rust
pavangudiwada
pavangudiwada
awesome-ai-sre

AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more

Score
43
โ˜… 58 โ‘‚ 19 +2/day
JavaScript
techlab-innov
techlab-innov
llmtrace

Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.

Score
63
โ˜… 54 โ‘‚ 1 โ€”
Python
localcloud-sh
localcloud-sh
localcloud

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

Score
0
โ˜… 50 โ‘‚ 1 โ€”
Go
megeezy
megeezy
Chameleon

Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent model selection.

Score
37
โ˜… 42 โ‘‚ 3 โ€”
Rust
ai-infra-curriculum
ai-infra-curriculum
ai-infra-performance-learning

AI Infrastructure Performance Engineer Learning Track - GPU optimization, inference optimization, and cost reduction

Score
14
โ˜… 41 โ‘‚ 9 โ€”
Python
biubiutomato
biubiutomato
TME-Agent

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

Score
0
โ˜… 36 โ‘‚ 2 โ€”
Python
MonetiseBG
MonetiseBG
circuit-breaker

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI workflows.

Score
32
โ˜… 30 โ‘‚ 3 โ€”
TypeScript
MasihMoafi
MasihMoafi
A-Modular-Kingdom

Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.

Score
26
โ˜… 29 โ‘‚ 2 โ€”
Python
monaccode
monaccode
astromesh

Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan&Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability.

Score
47
โ˜… 29 โ‘‚ 7 โ€”
Python
muxi-ai
muxi-ai
muxi

Deploy intelligence. Open-source infrastructure for AI agents in production.

Score
16
โ˜… 24 โ‘‚ 4 โ€”
sprklai
sprklai
zenii

Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 136 API endpoints. Desktop app, CLI, Telegram โ€” all connected. Rust-powered.

Score
0
โ˜… 23 โ‘‚ 5 โ€”
Rust
joyehuang
joyehuang
Learn-Open-Harness

๐Ÿค– Official Interactive Tutorial for OpenHarness โ€“ Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | ้ขๅ‘้›ถๅŸบ็ก€็š„ AI Agent ไบคไบ’ๅผๆ•™็จ‹

Score
11
โ˜… 19 โ‘‚ 3 +1/day
TypeScript
awaithumans
awaithumans
awaithumans-human-in-the-loop-ai-agents

Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.

Score
21
โ˜… 18 โ‘‚ 8 +1/day
Python
l0z4n0-a1
l0z4n0-a1
cognitive-claude

The meta-architecture behind a high-leverage Claude Code setup. Installed by the very tool it optimizes.

Score
42
โ˜… 17 โ‘‚ 16 โ€”
Python
paralleliq
paralleliq
piqc

Kubernetes scanner that discovers LLMs running on vLLM and extracts their deployment and runtime facts.

Score
0
โ˜… 13 โ‘‚ 1 โ€”
Python
redevops-io
redevops-io
redevops-rag

Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.

Score
5
โ˜… 10 โ‘‚ 0 โ€”
Python
Related Topics
#llm#ai-agents#rag#mcp#developer-tools#ai#openai#python#agentic-ai#vector-database#semantic-search#mcp-server

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly