RepoRadar helps AI developers, technical founders, and engineering leads answer three questions: What changed? What should I try? Which option fits this workflow?
Saved tools, searches, risks, movers, and newly reviewed candidates appear here first.
Check the newest retained change window when you are ready. Nothing is loaded until you ask.
Open the full change history →Today's rotating evidence-backed picks, selected from retained editorial or hands-on review. Each card shows its actual verification stage and opens the RepoRadar record first.
Sibyl-Labs/Sibyl-Memory is the MIT local-first agent-memory family that ships as **four PyPI packages** (`sibyl-memory-client`, `sibyl-memory-cli`, `sibyl-memory-hermes`…
yamadashy/repomix is a widely used MIT-licensed CLI and web tool that packs an entire codebase into one AI-friendly bundle, making it much easier to hand real repository context…
OpenAI Agents SDK for JavaScript/TypeScript is an MIT-licensed, provider-agnostic framework for building multi-agent and voice-agent workflows with tools, MCP support, handoffs…
kucherenko/jscpd is an MIT-licensed copy/paste detector for source code that supports 224+ formats, ships a token-efficient reporter, and exposes an MCP server so AI coding agents…
microsoft/presidio is an MIT-licensed, context-aware PII de-identification SDK from Microsoft that detects and anonymizes sensitive entities in text and images and ships pluggable…
MIT Microsoft cross-platform ML inference and training accelerator with ONNX standard support + hardware accelerators across CPU / GPU / NPU; 21,042* at verify time, last commit…
Repeat-visitor view: new signals, score movement, risk-label changes, and fresh try-now picks from the last 24 hours.
Tools, repos, agents, apps, and frameworks added in the last 24 hours.
New or newly tracked model-related signals in the last 24 hours.
No change detected in the last 24 hours.
No change detected in the last 24 hours.
No change detected in the last 24 hours.
Newly added or newly promoted try-now verdicts in the last 24 hours.
Tencent-Hunyuan/Hunyuan3D-WorldClaw is a 577-star open-source agentic framework (released 2026-08-10) that turns one open-ended prompt into an explicit, explorable, and editable op
NVIDIA-Nemotron-3.5-Lightning-30B-A3B is a 31.6B total / 3.6B active hybrid Mamba-Transformer open-weight model under NVIDIA Open Model License (with NVFP4 and BF16 variants), rele
mitkox/stolen-thoughts is the open-source artifact for 'Stealing Reasoning Traces from Proprietary LLM APIs', the 676pt #1 HN research piece for 2026-08-11; it demonstrates a concr
Arize-ai/openinference is a 1,140-star, Apache-2.0 OpenTelemetry SDK that instruments every major LLM / agent / vector-store framework (OpenAI, Anthropic, Gemini / Vertex, LangChai
infiniflow/infinity is a 4,669-star, Apache-2.0 AI-native database built for LLM applications that delivers incredibly fast hybrid search of dense vector, sparse vector, tensor (mu
Reviewed decision records from this run. Each passed the publication gate and links to its evidence and verification basis. Rotates weekly so returning visitors see fresh picks.
Why it's featured: it cleared our evidence and quality gates with the strongest overall signal in this run — the pick we’d point a newcomer to first.
Open decision record →Tested in a bounded workflowGitHub source ↗ for langchain-ai/langchainMomentum is a research lead, not a recommendation or editorial verification. Trending reflects engagement velocity and recency; each card shows its actual verification stage when one exists.
earendil-works/pi is an MIT agent toolkit that bundles a unified multi-provider LLM API, agent runtime, interactive coding-agent CLI, terminal UI…
Tested in a bounded workflow GitHub source ↗ for earendil-works/piDeepTutor HKUDS/DeepTutor is an Apache-2.0 open-source agent-native personalized learning platform from the HKU Data Science Lab that wraps LLM…
Research signal · Discovered, not yet verified GitHub source ↗ for HKUDS/DeepTutorCaveman JuliusBrussee/caveman is an MIT-licensed open-source skill/plugin for Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and 30+…
Research signal · Discovered, not yet verified GitHub source ↗ for JuliusBrussee/cavemanAirLLM lyogavin/airllm is an Apache-2.0 open-source Python library that runs 70B-class large language models in inference on a single 4GB GPU (and…
Research signal · Discovered, not yet verified GitHub source ↗ for lyogavin/airllmllama.cpp is an MIT-licensed C/C++ runtime for local LLM inference with GGUF models, server builds, Docker packaging, and a very large…
Research signal · Discovered, not yet verified GitHub source ↗ for ggml-org/llama.cppopen-code-review alibaba/open-code-review is an Apache-2.0 open-source AI-powered code-review CLI that originated as Alibaba Group's internal…
Research signal · Discovered, not yet verified GitHub source ↗ for alibaba/open-code-reviewSource-backed candidates chosen for further research. This is an editorial watchlist, not a measured growth ranking; each card shows its current catalog score and retained verification stage.
LangChain is a Python/JavaScript agent-engineering framework for composing model calls, tools, retrieval, structured outputs, multi-agent flows, and provider integrations.
An AI-powered job search system layered on Anthropic's Claude Code CLI.
N8n is a Fair-code workflow automation platform with native AI capabilities.
LocalAI is a self-hosted OpenAI-compatible inference server for running LLMs, embeddings, image/audio generation, speech, rerankers, and vision-style workloads locally.
Dify is a low-code platform for building LLM apps: chatbots, agent workflows, RAG knowledge bases, prompt orchestration, deployment, and operational monitoring.
LobeHub is a web-based agent operations hub for creating specialized AI agents, scheduling them as always-on jobs, attaching knowledge bases, and reviewing their run reports.
The latest tools entering the research catalog. Filtered by recency and catalog score for triage; inclusion is not editorial verification.
compozy/compozy is a 2,530-star, MIT 'operating system for AI agents' (CompozyOS) that wraps Claude Code, OpenClaw, Hermes, and Codex into a single Go-runtime agent OS handling...
vshulcz/deja-vu is a 628-star, MIT agent-session search engine that indexes the months of session history Claude Code / Codex / Pi / Aider / etc. already wrote to disk before...
MoonshotAI/checkpoint-engine is a 995-star, MIT middleware that updates LLM inference engine weights in-place during RL training (a critical step); updating Kimi-K2 (1T params)...
intel/auto-round is a 1,564-star, Apache-2.0 advanced quantization toolkit for LLMs and VLMs that achieves high accuracy at ultra-low bit widths (2-4 bits) with minimal tuning...
Arize-ai/openinference is a 1,140-star, Apache-2.0 OpenTelemetry SDK that instruments every major LLM / agent / vector-store framework (OpenAI, Anthropic, Gemini / Vertex...
AI-Hypercomputer/maxtext is a 2,387-star, Apache-2.0 Google Cloud reference JAX LLM training stack -- the canonical TPU-native implementation that ships reference training +...
The homepage separates reviewed decision surfaces from clearly labeled research signals. Search, filters, source links, risk labels, and all 2,513 ranked cards are available in the full catalog.
All ranked cards moved off the homepage.
Fresh and recently refreshed items in the public dataset.
Items with a practical verdict worth evaluating now.
Top evidence-linked useful signals.
RepoRadar is independently run. Tips help cover hosting, sources, and the time it takes to keep this useful. Never ranking. Never coverage. Never results.
V1 scoring prioritizes practical usefulness: usefulness 35%, novelty 18%, momentum 14%, maturity 10%, open-source/build quality 7%, evidence 6%, commercial/workflow potential 6%, setup ease 4%.
Gold is score ≥ 7.5 or the top 10% of eligible items with score ≥ 7.0. Silver starts at 6.5, Bronze at 5.25, and Low Signal catches low-value or low-signal items.
Gold requires Medium/High confidence, usable/official/cross-verified evidence or better, clear public descriptions, no excluded category, no weak or unclear AI relevance, and no fallback, triage-only, weak-evidence, low-signal, or low-transparency flags.
Risk remains a separate label and should not heavily reduce score unless severe. Transparency issues apply small penalties; hard exclusions still block publication.