StackMapby ShipWithAI
v1 · prototype

Stop building your AI stack from 40 open tabs.

A curated map of open-source AI & agent tools — and what actually pairs with what.

14 repos · 5 topics · curated by ShipWithAI

14 repos
↔ 2
google
agents-cli

CLI + agent-skills layer that turns your coding assistant into a Google Cloud agent-lifecycle expert: scaffold ADK projects, run and evaluate them, then deploy and publish to Gemini Enterprise.

agentsevals
alternative to LangGraph, Ragas
↔ 4
microsoft
AutoGen

Multi-agent conversation framework for building LLM applications with cooperating agents.

agentsevals
pairs well with Ragas, CrewAI
↔ 2
chroma-core
Chroma

Open-source embedding database for building AI apps with retrieval.

rag
pairs well with olmocr, LlamaIndex
↔ 1
RedPlanetHQ
core

Self-hosted, always-on "personal AI OS": watches your apps, keeps a persistent memory graph, and acts autonomously within guardrails — a product, not a library for building agents.

agentsorchestration
alternative to paperclip
↔ 4
joaomdmoura
CrewAI

Orchestrate role-playing, autonomous AI agents that collaborate on tasks.

agentsorchestration
alternative to AutoGen, LangGraph
↔ 1
stanfordnlp
DSPy

Program — don't prompt — your language models. Compile declarative pipelines into optimized prompts.

orchestrationrag
alternative to LangGraph
↔ 6
langchain-ai
LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

agentsorchestration
pairs well with LangSmith, paperclip
↔ 1
langchain-ai
LangSmith

Trace, test and monitor LLM apps in production.

evals
pairs well with LangGraph
↔ 3
run-llama
LlamaIndex

Data framework for connecting custom data sources to LLMs — ingestion, indexing, retrieval.

ragagents
pairs well with Ragas, olmocr
↔ 4
ollama
Ollama

Run Llama, Mistral and other open models locally with a single command and a clean API.

local
alternative to vLLM, AutoGen
↔ 3
allenai
olmocr

Open toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.

rag
pairs well with LlamaIndex, Chroma
↔ 4
paperclipai
paperclip

Open-source control plane for running fleets of heterogeneous AI agents as a "company" — bring your own agent, assign goals, org charts, budgets, governance, and an audited ticket system.

agentsorchestration
pairs well with LangGraph, CrewAI
↔ 3
explodinggradients
Ragas

Evaluation toolkit for your RAG and agent pipelines — faithfulness, relevance, and more.

evalsrag
pairs well with LlamaIndex, AutoGen
↔ 2
vllm-project
vLLM

High-throughput, memory-efficient inference and serving engine for LLMs.

local
alternative to Ollama, olmocr