Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
378 tools · showing 97–120
ToolObsidian Wiki
MemoryData Wrangling
Ar9av
Framework for an AI agent to build and maintain a knowledge base in an Obsidian vault using Karpathy's LLM Wiki pattern
productivityobsidianknowledge-basemarkdownskill
oMLX
Deployment
jundot
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
mlxlocal-firstmacosdesktop
FrameworkPipecat
Voice
pipecat-ai
Python framework for real-time voice and multimodal conversational agents, with composable pipelines over WebSockets or WebRTC
real-timemultimodalwebrtcvoice-agent
ToolPowerMem
Memory
oceanbase
Long-term agent memory with hybrid vector, full-text, and graph retrieval, LLM extraction, and time decay
long-term-memoryhybrid-retrievalvector-dbgraph-retrieval
ToolRepowise
Coding
repowise-dev
Indexes a codebase into a dependency graph, git history, docs, and code-health scores, exposed to MCP agents through nine tools
code-intelligencedependency-graphgit-analyticsstatic-analysis
Roboflow Inference
Deployment
roboflow
Server and SDK for running vision models locally or in the cloud behind a simple API.
videocomputer-visionobject-detectionon-devicedocker
ToolServer
Coding
triton-inference-server
Inference-serving software that deploys models from multiple frameworks across GPU and CPU on cloud, data center, and edge
gputensorrtonnxnvidia
ToolSnyk Agent Scan
Security
snyk
Security scanner for AI agents, MCP servers and agent skills.
prompt-injectiontool-poisoningvulnerability-scannersupply-chain
ToolUnsloth
TrainingInference
unslothai
Run and fine-tune open LLMs, vision, and audio models locally, with training claimed at up to 2x faster and up to 70% less VRAM
fine-tuneloragguflocal-first
Vibe-Trading
Research
HKUDS
Open-source research workspace connecting natural-language prompts to market data, strategy backtesting, and reports
financeproductivitymulti-agentalgorithmic-tradingfintech
ToolBrowser Use
Interface
browser-use
Python library that lets an LLM agent operate a web browser — opening pages, clicking, typing, and filling forms from a task description
browser-automationlangchainplaywright
FrameworkClaude Agent SDK
Coding
anthropics
SDK that exposes the Claude Code agent loop for building custom agents.
claudecoding-agentsdktool-calling
Garak
Security
NVIDIA
Command-line vulnerability scanner that probes LLMs for jailbreaks, prompt injection, data leakage, toxicity, and other failures
red-teamprompt-injectionvulnerability-scannercli
ToolGemini Notebook MCP CLI
Coding
jacob-bd
Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context Protocol (MCP) server, and AI agent skills.
notebooklmgeminiclimcp-server
ToolKTransformers
InferenceTraining
kvcache-ai
Framework for LLM inference and fine-tuning on CPU-GPU heterogeneous hardware, tuned for large mixture-of-experts models
moecpu-gpufine-tune
ToolLangsmith SDK
Coding
langchain-ai
Python and JavaScript SDKs for tracing, evaluating and monitoring LLM apps on the LangSmith platform
observabilityevaluationlangchain
ToolOpenInference
Monitoring
Arize-ai
OpenTelemetry auto-instrumentation that converts agent traces to OpenInference for Arize Phoenix / AX.
telemetryobservabilitylangchainllamaindex
ToolBentoML
Coding
bentoml
Python framework for turning AI models into inference APIs and multi-model serving systems
mlopsdockergpu
ToolBMad Method
Coding
bmad-code-org
Agile Ai Driven Development. A planning loop that runs before the IDE coding starts.
spec-drivenagileplanningskill
ToolClaude Skills
Coding
alirezarezvani
362 skills, 102 agents, and 644 Python tools packaged for Claude Code and twelve other coding agents
productivityskillplugincli
ToolCognee
Memory
topoteretes
Open-source AI memory platform that builds a self-hosted knowledge graph to give agents persistent long-term memory
knowledge-graphragvector-dblocal-first
ToolDograh
VoiceGenerative Media
dograh-hq
Self-hostable open-source voice AI platform for building inbound and outbound phone agents with a drag-and-drop workflow builder
local-firsttelephonyorchestrationpipecat
ToolDrawio Skill
Coding
Agents365-ai
Agent skill that turns natural language, codebases, IaC, or SQL into editable draw.io diagrams and image exports
productivitydiagram-generationdrawiomermaidskill
ToolEverOS
Memory
EverMind-AI
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Herme
raglocal-firstmarkdownsqlite