NousResearch/hermes-agent
A self-hosted assistant that runs commands, remembers past work and answers through six chat platforms and a terminal at once.
confident-ai/deepeval
Tests for the output of language models, written and run like ordinary unit tests and able to score with a local model.
lancedb/lancedb
An embedded retrieval library for embeddings, imported into a program and pointed at a folder, with no server to run.
NVIDIA/NeMo-Guardrails
Puts rules you write around a language model's input and output, and enforces them before the answer reaches anybody.
guardrails-ai/guardrails
Adds checks around a language model's output, covering content as well as shape.
dottxt-ai/outlines
It makes a model return valid structured output by constraining what the model is allowed to generate.
magnitudedev/magnitude
It measures the machine it is installed on, recommends a local AI model that will run well there, then downloads, tunes and serves it.
vectorize-io/hindsight
A memory store for AI agents that keeps what mattered from past sessions and hands the useful parts back, rather than replaying a whole conversation history.
langgenius/dify
A self-hosted platform for building applications on language models, with document search, tools, monitoring and an API in one deployable unit.
AnswerDotAI/rerankers 💎 hidden gem
A lightweight unified API over cross-encoder and reranking models — it sharpens which chunks surface in a retrieval step.
lobehub/lobe-chat
A self-hosted place to run and supervise several AI assistants, formerly the chat interface LobeChat.
mem0ai/mem0
A memory layer that lets an AI application remember a user between separate conversations.
huggingface/lighteval 💎 hidden gem
Runs more than a thousand standard public tests against a language model and reports the score.
mozilla-ai/llamafile
It packs a language model and the program that runs it into one executable file that works on macOS, Linux and Windows without being installed.
promptfoo/promptfoo
A test runner for prompts: you describe what a good answer looks like once, and it grades every model and every prompt against that description.
open-webui/open-webui
A self-hosted web interface for talking to AI models, with accounts, conversation history and document retrieval.
stanfordnlp/dspy
It improves the instructions you send a language model by measuring the answers instead of guessing.
MaartenGr/KeyBERT
Extracts the handful of phrases that describe a document by comparing the meaning of each candidate phrase with the meaning of the whole text.
MinishLab/semhash 💎 hidden gem
Fast semantic deduplication of text datasets — strips near-duplicate chat turns before topic modelling so clusters come out clean.
segment-any-text/wtpsplit 💎 hidden gem
Splits text into real sentences in 85 languages using small CPU models, including text with no punctuation.
vibrantlabsai/ragas
Scores how good a retrieval-based AI answer is, so a change can be shown to have helped or hurt.
pemistahl/lingua-py 💎 hidden gem
Knowing which language a paragraph is in — before you spend a model call finding out.
cheshire-cat-ai/core 💎 hidden gem
The opposite architecture from the LiteLLM-plus-custom-code path — batteries actually included: FastAPI, RAG, plugin loader, WebSocket chat, all in one image.
MinishLab/vicinity 💎 hidden gem
One interface over several nearest-neighbour backends — the throwaway in-memory index for a single conversation.
shap/shap
Per-prediction feature attribution — which of tsfresh's 700 features the surviving model actually leans on, and whether that reason is embarrassing.
optuna/optuna
Hyperparameter search that samples the promising regions and prunes hopeless trials early — a week of sweeps back as an afternoon.
HKUDS/LightRAG
Entity-and-relationship graph over documents with local and global query modes — GraphRAG's structure at a fraction of the cost, stored in PostgreSQL.
TutteInstitute/datamapplot 💎 hidden gem
Labelled data maps with proper label placement — a diagnostic for cluster naming and a shareable marketing image.
TutteInstitute/toponymy 💎 hidden gem
Names clusters at every level of a hierarchy using sub-cluster structure and sample documents rather than a bag of keywords.
apple/embedding-atlas
Apple's interactive embedding map with automatic cluster labelling — worth studying as a design reference for an overview screen rather than adding as a dependency.
LibreTranslate/LibreTranslate
Self-hosted machine-translation API — removes the per-character meter from running a bilingual site.
x-tabdeveloping/turftopic 💎 hidden gem
Five families of topic model behind one scikit-learn-style API — the head-to-head against BERTopic in one afternoon.
MaartenGr/BERTopic
The standard way to turn a long thread into named subtopics with a parent/child hierarchy and a timeline view.
feyninc/chonkie
Focused text-chunking library — semantic and recursive splitters that respect message boundaries, so subtopics come out clean.
microsoft/graphrag
Builds a knowledge graph from text, clusters it into nested communities, writes a summary for each level.
MinishLab/model2vec 💎 hidden gem
Distills sentence-transformers into static embeddings ~15x smaller and hundreds of times faster on plain CPU.
No repository in this area carries every tag you picked.
Get the next edition in your inbox
A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.
No tracking pixels. One click to leave. The archive stays free either way.
We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.