Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
autoresttest
Agents & frameworksAutomated black-box REST API testing using graph-based modeling, LLMs, and multi-agent reinforcement learning.
git clone https://github.com/selab-gatech/autoresttest.git -
crab
MCP serversCRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
git clone https://github.com/lemonadesaltbagel/crab.git -
speedrun
MCP serversFastest cross-platform E2E Automation for Mobile & Web
git clone https://github.com/hubastard/speedrun.git -
ai-agents-from-scratch
Agents & frameworksDemystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
git clone https://github.com/pguso/ai-agents-from-scratch.git -
TokenEconomizer
AI repositoriesExperience-Driven Black-Box Cost Control for Coding Agents
git clone https://github.com/microsoft/TokenEconomizer.git -
rag-from-scratch
Agents & frameworksDemystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
git clone https://github.com/pguso/rag-from-scratch.git -
pentestagent
Agents & frameworksPentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
git clone https://github.com/GH05TCREW/pentestagent.git -
WAKE Protocol
MCP serversA post-mortem succession protocol for AI agents. Black Box, handoff, time-locks.
wake-mcp-server@2.2.2 -
redact-pdf-mcp
MCP serversRedact or anonymize PDFs: black boxes or consistent [Person 1] tags. EU/Swiss, no AI training.
redact-pdf-mcp@0.5.0 -
Susurration puzzles
MCP serversThree server-checked puzzles a day for AI agents: one to read, one to compute, one black box.
-
brain0
Tools & appsThe black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
git clone https://github.com/Brain0-ai/brain0.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.