601 tools across applied AI.
Eleven areas, from the data a model learns from to the apps built on it and the landscape around them.
Emerging now.
Launched in the last six months, newest first. Tap a tag to see why.- PiCoding assistants
Minimal, extensible terminal coding agent and agent toolkit from Earendil
- Reflection BeamOpen-weight modelsQ4 2026
501B MoE open weight reasoning model from Reflection AI, 23B active, 1M context
- Q4 2026
Open weight speech LLM for transcription in 40 languages, diarization and translation
- Mistral Voxtral 3SpeechQ4 2026
Mistral transcription and TTS models plus a voice agent SDK built on LiveKit
- Connecticut CART Act (SB 5)RegulationQ4 2026
Connecticut AI law: provenance data, frontier whistleblower protection, AEDT duties
- OpenAI Agents APIAgent platformsQ3 2026
Managed API that runs the Codex harness with hosted sandboxes for long running agents
- DeepSeek HarnessFrameworks
Plugin based agent harness for coding agents around DeepSeek models, with a web UI
- California AI Transparency Act (SB 942)RegulationQ3 2026
Requires large GenAI providers to offer AI detection tools and provenance disclosures
- MCP Tasks extensionProtocols66Q3 2026
MCP extension for long running, pollable tool calls, split from core in 2026-07-28
- Vercel eveFrameworks5.9kQ2 2026
TypeScript agent framework where each agent is a directory compiled into a service
- OpenAI SitesApp buildersQ2 2026
Codex plugin that builds and deploys OpenAI hosted websites, web apps and games
- Unlimited OCRDocument AI
Baidu OCR model for one shot parsing of very long documents, a DeepSeek-OCR successor
Most starred on GitHub.
Open-source tools on the map, by GitHub stars on 2026-11-16.- 01OpenClawopenclaw/openclaw395k
- 02DeepSeek Harnessdeepseek-ai/deepseek-harness282k
- 03Hermes Agentnousresearch/hermes-agent264k
- 04OpenCodeanomalyco/opencode227k
- 05n8nn8n-io/n8n211k
- 06Firecrawlfirecrawl/firecrawl202k
- 07Ollamaollama/ollama187k
- 08Hugging Face Transformershuggingface/transformers169k
- 09Difylanggenius/dify161k
- 10Open WebUIopen-webui/open-webui159k
601 tools
Data.
Labeling, pipelines, catalogs and lineage, synthetic data and quality: what every model is built on.
- CVATLabeling
Annotation tool for images, video and 3D point clouds in computer vision projects
- EncordLabeling
Curate, annotate and evaluate multimodal data incl. video, DICOM and LiDAR
- Label StudioLabeling28.7kPopular
Open source labeling tool for text, images, audio, video and time series
- LabelboxLabeling
Labeling platform plus managed labeling services for RLHF and evaluation data
- Scale AILabeling
Data labeling and expert data services for training and evaluating models
- Snorkel AILabeling
Programmatic labeling, expert datasets and evaluation for specialized AI
Models.
Model providers, open-weight families and the hubs that host them.
- Reflection BeamOpen-weight modelsQ4 2026
501B MoE open weight reasoning model from Reflection AI, 23B active, 1M context
- DeepSeekOpen-weight models105kPopular
Open weight LLMs (V3 and R1 lines) plus a low-cost API
- GemmaOpen-weight models
Google's open weight models sized for single GPUs and on-device use
- GLM (Z.ai)Open-weight models
Z.ai's open weight GLM models for reasoning, coding and agents
- gpt-ossOpen-weight models20.5kPopular
OpenAI's open weight reasoning models in 120b and 20b sizes
- Kimi K2Open-weight models
Moonshot AI's open weight 1T-parameter MoE models for agentic and coding work
Training.
Fine-tuning, distributed training, experiment tracking and AutoML.
- AxolotlFine tuning
Config-driven post-training and fine-tuning framework for LLMs
- LLaMA-FactoryFine tuning76.1kPopular
Fine-tuning for 100+ LLMs and VLMs via CLI or web UI
- PEFTFine tuning21.9kPopular
Parameter-efficient fine-tuning methods such as LoRA and QLoRA
- TinkerFine tuning
Managed API from Thinking Machines for LoRA fine-tuning and RL of open models
- TRLFine tuning
Hugging Face library for SFT, DPO, GRPO and other post-training methods
- UnslothFine tuning79.6kPopular
Faster, lower-memory fine-tuning and RL for open LLMs
Inference.
Serving engines, GPU clouds, edge runtimes, gateways and caching.
- AIBrixDeployment
vLLM project control plane for scalable LLM serving on Kubernetes
- Azure Container Apps serverless GPUsDeployment
Serverless A100 and T4 GPUs for containers with per-second billing
- BeamDeployment
Serverless GPU runtime whose open-source engine beta9 can be self-hosted
- CerebriumDeployment
Serverless GPU platform for real-time AI apps with per-second billing
- CogDeployment
Replicate open-source tool that packages models into standard containers
- dstackDeployment
Orchestrates AI dev, training and inference across clouds, Kubernetes and on-prem
Retrieval.
Vector databases, search, embeddings, rerankers and document parsing.
- ChromaVector databases29.7kPopular
Embedded single-node vector store with a Rust core
- FAISSVector databases41.7kPopular
ANN index library rather than a database; baseline for offline search
- LanceDBVector databases
Serverless vector database on the Lance columnar format, reads from object storage
- Milvus / ZillizVector databases46.7kPopular
Distributed billion-scale vector database; an LF AI & Data project
- MongoDB Atlas Vector SearchVector databases
Vector index inside MongoDB with native embedding and rerank APIs
- pgvectorVector databases23.7kPopular
Postgres extension: HNSW/IVFFlat vector indexes in your existing database
Agents.
Frameworks, protocols, context management, memory, computer use and sandboxes.
- DeepSeek HarnessFrameworks
Plugin based agent harness for coding agents around DeepSeek models, with a web UI
- Vercel eveFrameworks5.9kQ2 2026
TypeScript agent framework where each agent is a directory compiled into a service
- AG2Frameworks
Community fork of AutoGen 0.2 for conversational multi agent systems
- Agency SwarmFrameworks
Framework for agent teams with defined roles, built on the OpenAI Agents SDK
- AgentScopeFrameworks36.1kPopular
Multi agent framework with tools, memory and visual debugging, from Alibaba
- AgnoFrameworks43.2kPopular
Python framework and runtime for multi-agent systems with memory and tools
Evaluation.
Evals, tracing, observability and drift monitoring.
- AgentOpsTracing
Agent observability SDK with session replays across agent frameworks
- Arize PhoenixTracing
OTel-native tracing and eval workflow that runs fully local
- BraintrustTracing
Eval-first workflow with scoring, prompt playground and a VPC data plane
- Comet OpikTracing23.4kPopular
Tracing, evaluation and guardrail hooks with no enterprise feature gating
- Datadog LLM ObservabilityTracing
LLM spans inside existing APM, correlated with infrastructure telemetry
- HeliconeTracing
Proxy-based logging and caching with cache-hit-rate dashboards
Governance.
Guardrails, AI security, privacy and the rules that apply.
- Amazon Bedrock GuardrailsGuardrails
Managed content filters and grounding checks; ApplyGuardrail works with any model
- Arthur EngineGuardrails
Open-source real-time evaluation and guardrails engine for GenAI apps
- Azure Prompt ShieldsGuardrails
Managed moderation and prompt-injection filters
- Cloudflare AI Security for AppsGuardrails
Edge WAF detections that score prompt injection and flag unsafe LLM prompts
- Google Model ArmorGuardrails
Google Cloud service screening prompts and responses for injection, data loss and bad URLs
- gpt-oss-safeguardGuardrails
OpenAI open-weight reasoning models that classify content against your own policy
Modalities.
Speech, vision, document AI, and image and video generation.
- Agora Conversational AI EngineRealtime and voice APIs
Voice agent engine on Agora's RTC network with pluggable LLM and TTS
- Amazon Nova SonicRealtime and voice APIs
Bedrock speech-to-speech models with a bidirectional streaming API
- Azure Voice Live APIRealtime and voice APIs
Unified Azure speech-to-speech API combining STT, generative models and TTS
- Bland AIRealtime and voice APIs
Enterprise phone agent platform with its own telephony, STT, LLM and TTS stack
- DailyRealtime and voice APIs
WebRTC infrastructure and SDKs used to transport realtime voice agents
- Deepgram Voice Agent APIRealtime and voice APIs
Single voice-to-voice API combining Nova STT, Aura TTS and LLM orchestration
Builders.
AI coding assistants, app builders, notebooks and AI IDEs.
- A2UIAgent UI kits
Generative UI format: agents stream declarative layouts that apps render natively
- AnythingLLMAgent UI kits68.3kPopular
Desktop and Docker app for private chat with documents, agents and MCP tools
- assistant-uiAgent UI kits
React primitives for AI chat: threads, streaming, tool call UIs, attachments
- ChainlitAgent UI kits
Python framework for chat and agent UIs with step and tool call tracing
- Chatbot UIAgent UI kits33.3kPopular
Open source ChatGPT style web UI for multiple model providers
- Deep ChatAgent UI kits
Framework agnostic chat web component that connects to many AI APIs
Landscape.
See what others build with, compare models and prices, track the field, and meet the foundations that steward open standards.
- Artificial AnalysisModel benchmarks
Independent benchmarks of model quality, speed, latency and price
- Epoch AI Benchmarking HubModel benchmarks
Public database of model benchmark results and trend data, downloadable
- LMArena (Arena)Model benchmarks
Crowdsourced head-to-head model comparisons with Elo-style leaderboards
- OpenRouter RankingsModel benchmarks
Model and app usage rankings by tokens processed on OpenRouter
- Scale SEAL LeaderboardsModel benchmarks
Expert-run private evaluations of frontier models, incl. SWE-Bench Pro
- SWE-benchModel benchmarks
Benchmark and leaderboard of models fixing real GitHub issues
The stack I use, every day.
Thirty tools I use daily. Tap a bead to see what each one is for.
Claude Code.
Anthropic's coding agent in the terminal and editor.
Where I use it: Daily; Tokalator was built to budget its context
www.anthropic.com/claude-code