AetherAI3/Unlimited-Context-LLM

Support LM Studio as a backend alongside Ollama about 3 hours ago

help wanted

26

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

Python

#ai-agents#context-engineering#infinite-context#llama#llm#llm-memory#local-first#local-llm#local-rag#long-context#memory#mistral#ollama#ollama-rag#persistent-memory#python#qwen#rag#retrieval-augmented-generation#vector-search

Extend `aether-context status` with store size, last index time, and embedding model about 3 hours ago

good first issue

AetherAI3/Unlimited-Context-LLM

26

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

Python

#ai-agents#context-engineering#infinite-context#llama#llm#llm-memory#local-first#local-llm#local-rag#long-context#memory#mistral#ollama#ollama-rag#persistent-memory#python#qwen#rag#retrieval-augmented-generation#vector-search

Docs: 5-minute Windows quickstart for Ollama users about 3 hours ago

documentation good first issue

AetherAI3/Unlimited-Context-LLM

26

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

Python

#ai-agents#context-engineering#infinite-context#llama#llm#llm-memory#local-first#local-llm#local-rag#long-context#memory#mistral#ollama#ollama-rag#persistent-memory#python#qwen#rag#retrieval-augmented-generation#vector-search

Example: give a coding agent memory that survives process restart about 3 hours ago

good first issue

AetherAI3/Unlimited-Context-LLM

26

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

Python

#ai-agents#context-engineering#infinite-context#llama#llm#llm-memory#local-first#local-llm#local-rag#long-context#memory#mistral#ollama#ollama-rag#persistent-memory#python#qwen#rag#retrieval-augmented-generation#vector-search

Benchmark: recall quality at 100k / 1M / 10M tokens about 3 hours ago

help wanted

AetherAI3/Unlimited-Context-LLM

26

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

Python

#ai-agents#context-engineering#infinite-context#llama#llm#llm-memory#local-first#local-llm#local-rag#long-context#memory#mistral#ollama#ollama-rag#persistent-memory#python#qwen#rag#retrieval-augmented-generation#vector-search

Open Issues Need Help