Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
gsd-skill-creator
SkillsIntroduces a comprehensive agent-based framework for guided software development (GSD)
git clone https://github.com/Tibsfox/gsd-skill-creator.git -
claude-reflect-system
SkillsContinual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes
git clone https://github.com/haddock-development/claude-reflect-system.git -
claude-smart
Agents & frameworksTurns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
git clone https://github.com/ReflexioAI/claude-smart.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
LeAgent
Agents & frameworksOpen-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in one self-hostable stack.
git clone https://github.com/vixues/LeAgent.git -
Marrow
MCP serversEvidence-grounded, graph-connected, correctable memory for agents.
@marrowid/cli@1.0.10 -
Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。
git clone https://github.com/KarmenLoop/user-behavior-personalization.git -
CountdownsHQ
Public APIsDates and timezone-correct countdowns for 150+ holidays and observances in 18 countries
-
evalstats
PromptsStatistical inference for AI evaluations, from model comparisons to corrections for LLM judge bias, optimized for small sample sizes. All defaults battle-tested in Monte Carlo simulations.
git clone https://github.com/ianarawjo/evalstats.git -
English Translator and Improver
PromptsI want you to act as an English translator, spelling corrector and improver. I will speak to you in any language and you will detect the language, translate it and answer in the corrected and improved version of my…
-
hangulport
MCP serversKorean NLP via Bareun: morphology, dictionary search, tokenize, and grammar correction.
@reneturcios/hangulport@0.1.0 -
appCN
MCP serversInstall & correctly use appCN React Native / Expo components, streamed from the live registry.
@app-cn/mcp@0.1.2 -
justcaptions
MCP serversAudio transcription, caption correction, translation and 16 video caption styles.
-
rash
MCP serversTranspile Rust code to POSIX-compliant shell scripts with formal correctness guarantees
-
Palinode
MCP serversInspectable, correctable project memory in git-versioned Markdown for AI agents.
palinode@0.24.1 -
Oort
MCP serversMemory for AI agents that stays correct as facts change.
oortmem@0.10.0 -
Quantum Expectations
MCP serversQuantum error-correction feasibility: success probability, qubit overhead, records, trends.
-
shikamaru
MCP serversProvably correct day-count, calendar, business-day, and schedule math, verified against QuantLib.
@jayofemi/shikamaru@1.1.1 -
WPGuard MCP
MCP serversWordPress edit previews, scoped correction checks, and change records for trusted operators.
ghcr.io/cgallic/wpguard-mcp:0.4.0 -
TenorOps
MCP serversRead restaurant operations, assigned tasks, checklist runs, and corrective actions in TenorOps.
-
Skeletable
MCP serversSource-backed public tables with citations, claim checks, and reviewable corrections.
-
text2sql
MCP serversAsk any SQL database in natural language. Agent explores schema, writes SQL, self-corrects.
text2sql-mcp@0.1.2 -
cal-scheduler
MCP serversTimezone-correct CalDAV scheduling MCP server with validated recurrence and single-occurrence edits.
cal-scheduler-mcp@1.1.3 -
japan-ux
MCP serversJapanese UI + UX correctness for AI coding agents — typography, forms, keigo, JLReq checks.
japan-ux-mcp@2.1.1
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.