FastBuilderAI/memory
FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embedding and vectors entirely), AI memory and LLM queries by upto 100% as in the huggingface benchmarks(22+ SOTA)
This project helps AI agents understand complex information better by organizing unstructured text data, like enterprise codebases or documents, into a structured, navigable 'memory map.' It takes raw text and transforms it into logical components, blocks, functions, and rules that AI can follow precisely. This is for AI developers building reliable AI agents that need to perform multi-step reasoning and access specific information without errors.
Use this if you are building AI agents that need to accurately understand and navigate large, complex text datasets to answer multi-hop queries without making up information (hallucinations).
Not ideal if your AI tasks only involve simple keyword matching or semantic similarity searches on small, less complex datasets.
Stars
20
Forks
3
Language
HTML
License
—
Category
Last pushed
Apr 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/FastBuilderAI/memory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
syncreus/syncreus-eval
Evaluate your LLM apps with one function call. Hallucination detection, RAG scoring, and agent...
bevinkatti/rag-harness
⚡ CLI to Evaluate and Compare RAG systems with RAGAS-style scoring
verifywise-ai/verifywise-eval-action
GitHub Action & Python SDK to evaluate LLMs in CI/CD — gate PRs on correctness, faithfulness,...
masaakisakamoto/memory-os
Deterministic continuity for AI systems. Detect and repair inconsistencies across sessions — not...
CjTruHeart/abundance-codex
Evidence-anchored narrative dataset that shifts AI reasoning from scarcity-default to...