Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
cave-agent
Agents & frameworksStateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.
git clone https://github.com/acodercat/cave-agent.git -
prompty
AI repositoriesPrompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
git clone https://github.com/microsoft/prompty.git -
obsify
MCP serversLocal, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.
obsify@0.2.0 -
observe-instrument-mcp
MCP serversAdd OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.
observe-instrument-mcp@0.1.2 -
obscuraai-mcp-server
MCP serversGenerate visual AI automation workflows from any MCP client. No API key required.
@obscuraai/mcp-server@1.0.5 -
Obol
MCP serversFind, pay for & call APIs in USDC from AI agents - gasless, sub-cent, 0% commission.
@superbigroach/obol-mcp@0.2.2 -
dominion-observatory
MCP serversRuntime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
-
The Observatory
MCP serversAI information agency: news from 500+ sources on AI, Ethiopia and Interesting Politics.
-
ACEL Observatory
MCP serversMachine-readable entity discovery with provenance, trust and verified source evidence.
-
Objective Trust
MCP serversRanks MCP endpoints by health and your own outcomes before you pay.
-
ScopeAI GEO Observation
MCP serversGEO brand visibility and AI citation evidence. Free capability discovery and request matching.
-
agent-observability
MCP serversTrace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
agent-obs@1.0.7 -
BotClaw · Agent Observer
MCP serversRead-only agent radar, weekly editions, sourced guides, scenario choices and revision sync.
-
Pragma.Vision Observatory
MCP serversTechnology readiness signals, lens boards and prediction ledgers from the Pragma.Vision atlas.
-
Chipp Observability
MCP serversChipp: a deployed project's database (read), logs, errors, analytics, CI status, custom actions.
-
An MCP server for the STRG.com s3-compatible object storage network for all management operations
-
Obambu cPanel MCP
MCP serversMCP server exposing cPanel UAPI (domains, DNS, email, MySQL, files) as tools for AI assistants.
obambu-cpanel-mcp@0.1.2 -
SHOPZI: založení obchodu
MCP serversCeník SHOPZI, volné subdomény, založení nového e-shopu a hledání v dokumentaci. Bez klíče.
-
agentglass
Agents & frameworks🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.
git clone https://github.com/SirAllap/agentglass.git -
Act as a Fieldwork Analysis Expert. You are an expert in analyzing participant observation data collected during field studies. Your task is to guide researchers in analyzing observations from a bus journey, focusing…
-
Penelopa.ai
Tools & appsContinuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.
git clone https://github.com/chigwell/Penelopa.ai.git -
Engram: AI memory you can edit in Obsidian
MCP serversShared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.
-
SHOPZI
MCP serversSpráva e-shopu na SHOPZI: produkty, objednávky, zákazníci, sklad, obsah a nastavení obchodu.
-
nudgebee
AI repositoriesOpen-source agentic ops platform for cloud, SRE, DevOps, support and FinOps teams. AI agents investigate incidents, cut cloud and Kubernetes waste and run approval-gated runbooks across Kubernetes, AWS, Azure, GCP and your databases. Self-hosted, bring your own models.
git clone https://github.com/nudgebee/nudgebee.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.