convez.ai
Agente
MukundaKatta

claude-workspace

MukundaKatta/claude-workspace

Ver no GitHub
InicialPluginScore · de 0 a 100

Central index of all @MukundaKatta repos, wired for Multica agents and Claude Code

Instalação

$npx convez-ai MukundaKatta/claude-workspace

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 3 meses
Versão
—
Issues abertas
2
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

claude-workspace

Central index of every repo under @MukundaKatta, wired up so agents (via Multica, Claude Code, Codex, OpenClaw, Cursor) can reason across the whole portfolio.

This repo does not hold source code. It is the map. Point your agent at this README and it knows which repo a task belongs to.

Portfolio at a glance

Count
Total public repos945
Original (non-fork)429
Active (non-fork, non-archived)391
Forks516
Archived306

Quick start with Multica

Multica turns coding agents into teammates you can assign issues to. Set it up once, point it at these repos, stop copy-pasting prompts.

# Install Multica CLI (macOS / Linux)
brew install multica-ai/tap/multica

# One-command configure + auth + start local daemon
multica setup

Then provision this workspace's skills and agents in one shot:

git clone https://github.com/MukundaKatta/claude-workspace.git
cd claude-workspace
./scripts/provision.sh

provision.sh checks you're logged in, finds your runtime, imports the 5 skills from .multica/skills/, and creates one agent per CLI it detects on your PATH (Claude, OpenClaw, Gemini, Codex, OpenCode, Cursor, Pi, Hermes). Re-running is safe — it skips skills and agents that already exist.

After that, assign any issue from any of your repos to one of the new agents. The agent claims the work on your local runtime, executes, streams progress, and reports back.

Full CLI reference: multica-ai/multica CLI_AND_DAEMON.md. Self-host: SELF_HOSTING.md.

Using this workspace with Claude Code

  1. Clone this repo and open it in Claude Code:
    git clone https://github.com/MukundaKatta/claude-workspace.git
    cd claude-workspace
    claude
    
  2. Claude reads CLAUDE.md on startup and picks up the full portfolio map.
  3. Ask "open the alertiq repo and add a new rule" and Claude knows exactly where to go.

Active projects (curated)

A curated cut of the 391 active originals, sorted by theme. The full list lives in data/repos.ndjson and is regenerated by scripts/refresh.sh.

AI agents & agent infrastructure

RepoStackDescription
karnaTypeScriptSelf-hosted personal AI assistant with multi-channel messaging, extensible skills, and semantic memory
AgentRAGPythonModular RAG pipeline — chunking, embedding, retrieval, reranking with pluggable vector stores
astra-agentTypeScriptStandalone agent runtime — tool execution, context management, multi-model routing
agentmemPythonMemory management — short-term, long-term, semantic memory with automatic consolidation
SwarmKitPythonMulti-agent framework with voting and consensus
swarmcastPythonUniversal swarm intelligence engine
agent-stackJavaScriptReliability stack landing page for the @mukundakatta/agent* libs (fit, guard, snap, vet, cast)

LLM tooling & evals

RepoStackDescription
EvalBenchPythonBLEU, ROUGE, semantic similarity, custom metrics
evalharnessTypeScriptRed teaming, regression testing, CI/CD for AI
TokenWisePythonToken counting, cost estimates, budget tracking across LLM providers
llm-bench-cliPythonFast CLI for benchmarking local LLMs
HybridFindPythonHybrid BM25 + vector search with Reciprocal Rank Fusion
oss-contributionsPythonPublic hub for AI SDK, MCP, and eval contributions
agent-eval-public-notesMarkdownReusable notes for evaluating tool-using AI agents — operational scorecard, trajectory replay debugging, RAG guardrail smoke tests

AWS Bedrock production

A three-library suite for teams running Anthropic Claude on AWS Bedrock at production scale. Built around the failure modes documented in bedrockcache's research log — including the HN $37,901 prompt-caching incident. Each library is independent; they compose without depending on each other. Zero runtime dependencies on any of them.

The landing repo is bedrock-production-stack — story + comparison vs Phoenix/Langfuse/Helicone/LiteLLM + a 50-line runnable example that wires all three together. Mirrors the agent-stack JS pattern.

RepoStackDescription
bedrock-production-stackPythonFront-door / landing repo for the three libraries below. Includes a 50-line runnable example that exercises all three. CI green on Python 3.10–3.13.
bedrockcachePythonStatic auditor that catches "this Bedrock call won't actually cache" before the request goes out. Six backends: bedrock-converse, bedrock-invoke-anthropic, AnthropicBedrock, LiteLLM, Strands, pydantic-ai. CLI + pytest assertion. v0.1.0 on PyPI + Homebrew + GHCR.
bedrockstackPythonThree primitives every Bedrock team rewrites: Bedrock-aware RetryPolicy (knows the retryable codes vs the never-retry list), thread-safe cost Ledger with scope tags + grouped totals, wrap_stream() to normalize the AnthropicBedrock-vs-native streaming-error parity gap. v0.1.0 on PyPI.
ragvitalsPythonFive-dimensional production drift detection for RAG: query distribution, retrieval relevance, embedding drift, response quality, judge drift. Library not platform — bring-your-own time-series store via Sink protocol. Constant-baseline-aware classifier so a perfectly stable system that suddenly drops still alarms. v0.1.0 on PyPI.
ragvitals-gemma-demoPythonCompanion demo for the dev.to challenge series. Exercises ragvitals across a Claude↔Gemma 4 model swap (synthetic + real-models paths), a pgvector + pgai + Ollama stack, a self-auditing Postgres path, and a 60-line Redis Streams sink. CI green on Python 3.10–3.13.

MCP (Model Context Protocol)

RepoStackDescription
MCPForgePythonBuild, test, deploy MCP servers — scaffolding + hot-reload + registry publishing
mcp-quickservePythonMinimal toolkit for creating MCP servers from plain functions with decorators
mcp-toolkitTypeScriptToolkit for building MCP servers and clients
mcpcheckTypeScriptMCP config linter for Claude Desktop, Cursor, Cline, Windsurf, Zed
rag-knowledge-baseTypeScriptRAG knowledge base with FastAPI, ChromaDB, Claude API streaming

Dev tooling

RepoStackDescription
patchlyTypeScriptAI code review bot — flags bugs, suggests fixes, explains why
prdforgeTypeScriptAI workbench for PMs — synthesize calls, draft PRDs, ship roadmaps
waitlist-apiTypeScriptShared waitlist backend for landing pages on Vercel KV

Security

RepoStackDescription
alertiqPythonAI SOC analyst — alert triage, correlation, incident response
vulnfixPythonAI vulnerability scanner with fix suggestions
prithviPythonContainer security scanner
rag-guardrails-actionYAMLGitHub Action: scan retrieved-text fixtures for prompt-injection + vector-poisoning before they reach your LLM. Wraps both npm libs. v0.1.0.
prompt-injection-shield-demoPythonStreamlit demo of the prompt-injection scanner. Mirrored as a Hugging Face Space at mukunda1729/prompt-injection-shield-demo.
prompt-injection-evalCSV/JSONLHand-curated evaluation dataset for prompt-injection detectors: 74 rows across 9 categories (classic override, URL exfil, system impersonation, tool hijack, role override, encoded, indirect RAG poison, borderline, benign). Companion to prompt-injection-shield.
prompt-injection-shield-cliPythonpis-scan CLI wrapper around prompt-injection-shield-py. Available on PyPI, Homebrew, and GHCR. v0.1.0.
awesome-prompt-injection-defenseMarkdownCurated list of detection libs, RAG guardrails, eval datasets, demos, and papers for defending LLMs against prompt injection. CC0.
homebrew-tapRubyPersonal Homebrew tap. brew tap MukundaKatta/tap then brew install pis-scan.
rag-guardrails-paperLaTeXPreprint bundle for small-rule RAG guardrails: prompt injection + vector poisoning checks. Zenodo + Figshare + OSF + Kaggle.

RAG guardrails: external mirrors and surfaces

SurfaceURL
GitHub Pages (awesome list)https://mukundakatta.github.io/awesome-prompt-injection-defense/
Hugging Face Space (live demo)https://huggingface.co/spaces/mukunda1729/prompt-injection-shield-demo
Hugging Face Datasethttps://huggingface.co/datasets/mukunda1729/prompt-injection-eval
Kaggle Datasethttps://www.kaggle.com/datasets/mukundakatta/prompt-injection-eval-set
OSF Projecthttps://osf.io/nxyvr
PyPI (pis-scan)https://pypi.org/project/prompt-injection-shield-cli/
GHCR containerghcr.io/mukundakatta/pis-scan
Codeberg mirrorshttps://codeberg.org/MukundaKatta (4 repos)
GitLab mirrorshttps://gitlab.com/mukunda.vjcs6 (4 repos)
Replithttps://replit.com/@mukundavjcs6

Healthcare & wellness

RepoStackDescription
pranaPythonVital sign estimation from smartphone camera (HR, BP, SpO2, resp rate)
clinical-nlp-toolkitPythonNLP for clinical notes — entity extraction, coding, summarization
OradentTypeScriptDental practice management platform
chartlyTypeScriptAI SOAP-note scribe — cuts physician documentation time by 75%
platewiseTypeScriptSnap-a-plate nutrition tracker with macros, calories, and gaps
moontrackTypeScriptPrivacy-first cycle tracker with energy and sleep coaching
breathlyTypeScriptGuided breathwork for anxiety, sleep, and focus
restwiseTypeScriptAI sleep coach plugging into Oura, Whoop, Apple Watch
samecrewTypeScriptPeer-matched emotional support — new dads, immigrants, first-time founders
tintalkTypeScriptText-first teen mental health with human escalation

Education

RepoStackDescription
mathkinTypeScriptK–10 AI math tutor — homework, test prep, drills
readmateTypeScriptReading coach for first-graders with parent progress reports
codegardenTypeScriptAI coding tutor for teens — games, Discord bots, mods
crammrTypeScriptAI prep tutor for JEE, NEET, MCAT, CAT, bar
fluentpalTypeScriptAI voice tutor for English — real conversations, gentle corrections
primeintTypeScriptAI mock interviews with role-specific questions and feedback
scholarTypeScriptResearch assistant — synthesizes sources into an outline

SMB products

RepoStackDescription
Office3HTMLOfficethree Technologies — AI products for small businesses
voiceagentTypeScriptAI voice receptionists for SMBs
answerooTypeScript24/7 AI receptionist — dentists, salons, law firms, trades
fanoutTypeScriptAgentic content studio — one product, 5 drafts, 15 channels
postopsTypeScriptAI captions, hashtags, and scheduling from a photo
pitchrTypeScriptPolished agency proposals in ten minutes
replynowTypeScriptAI drafts responses to every Google review in your voice
quoteboltTypeScriptContractor quoting — labor, materials, markup from plain text
pricematchTypeScriptFreelance pricing backed by industry rates
featherTypeScriptSolo-founder CRM — clients, deals, follow-ups without Salesforce
chaptrTypeScriptPaid community platform — messaging, events, gated content
followyTypeScriptAI meeting teammate — Jira tickets, Slack follow-ups, next calls
triagedTypeScriptAI inbox autopilot — sort, summarize, draft replies
solo-shopTypeScriptCreator commerce — start selling with a single photo
storieTypeScriptNiche storefronts for potters, bakers, coaches, authors
platemapTypeScriptMenu digitization with calories, allergens, QR-ready
buildcostPythonAI construction cost estimation from blueprints
bustrackTypeScriptReal-time school bus tracking with AI arrival prediction
amogha-cafeJavaScriptFull-stack Firebase restaurant app with ordering, kitchen display, QR dine-in
StockPulseTypeScriptStock market analytics and portfolio dashboard
SpotRankJavaScriptAI SEO audit and local business ranking

Creative & interfaces

RepoStackDescription
DesignLintTypeScriptUI/UX linter — accessibility, contrast, spacing
analystaiTypeScriptAI spreadsheet for analyzing large doc sets with citations
artigenTypeScriptAI art community on React Native + Expo + Supabase
chetanaTypeScriptAI consciousness research — 14 indicators from 6 scientific theories
nexus-searchTypeScriptAI intelligence engine on Next.js 14 + Claude + Brave Search
animeifyTypeScriptPhoto-to-anime in six seconds — Ghibli, Shinkai, shonen
headshotlyTypeScriptStudio-grade headshots from selfies
inkwiseTypeScriptAI tattoo designer with flash and on-skin preview
memoryloopTypeScriptRestore and animate old family photos
petraitTypeScriptAI portraits of your pet in royal, Renaissance, astronaut styles
polydubTypeScriptLip-synced video dubbing in 40+ languages
thumbliftTypeScriptMrBeast-quality thumbnails in thirty seconds
twincastTypeScriptClone yourself on video — any script, any language
rifflyTypeScriptStudio-quality vocals from ethically licensed artist voices
quilledTypeScriptAI newsletter ghostwriter in your voice
pindropTypeScriptIndie podcast editor — chapters, show notes, transcripts
flickupTypeScriptPodcast-to-shorts — sixty vertical clips with captions
gridcraftTypeScriptVisual Instagram grid planner for six months of posts

Consumer & lifestyle

RepoStackDescription
fridgechefTypeScriptDinner ideas from a photo of your fridge
cancelyTypeScriptFind and cancel forgotten subscriptions in one tap
boxitTypeScriptAI receipt filing — email, photo, or forward
rightsideTypeScriptPlain-English legal copilot — landlords, tenants, freelancers
signoffTypeScriptRead contracts like a lawyer — red flags and negotiable terms
reloodTypeScriptLocal resale for kids clothes, toys, and gear
sendrailTypeScriptStablecoin remittance — US/GCC to India, Philippines in seconds
gigledgerTypeScript1099 income, expenses, and estimated taxes
applybotTypeScriptAI job auto-applier — one profile, thousands of tailored apps

Personal, data, community

RepoStackDescription
mukunda-aiTypeScriptPersonal portfolio — mukundakatta.dev
MukundaKattaPythonProfile README
claude-workspaceShellThis repo — central index for agent tooling
heimdallPythonCurated AI system prompts
sadhakJavaScriptAI job search pipeline on Claude Code
rnhtTypeScriptRudra Narayana Hindu Temple community platform
survivalnodeTypeScriptOffline survival computer with tools, maps, reference data
sports-betting-analyticsPythonProp bet analyzer — odds aggregation + ML models for +EV opportunities
carpriceJupyterCar price prediction with regression
Employee_Management_System_ProjectHTMLEmployee management with RBAC
TeamZion——

The ADAPT framework — which lib for which stage

Most people stuck on AI are stuck between dabbling and amplifying. They touch 30 tools, master none, and tell themselves they're "keeping up" while their co-worker at the next desk is shipping. The 5 stages below map each step to libraries in this stack so you know what to pick up when.

StageWhat you doLibraries from the stack
A — AcknowledgeStop telling yourself AI will not change your job. It already has. 11.7% of every job today is automatable right now.—
D — DabbleTouch 20+ tools across text, image, voice, code, automation. Build a vibe for what is possible.Skim every README under @MukundaKatta and the @mukundakatta GitLab namespace. No deep dives yet.
A — AmplifyPick 3–5 tools and push them to failure. Stop reading articles and start using them on paid work.If you build agents: skill-runtime + agent-tools + agent-memory. If you ship to prod: agentsnap + agentguard + agentvet.
P — Problem solveStop thinking in tools. Stitch 5–6 of them into one workflow that solves a real problem someone will pay for.agent-team (fan-out), tool-bridge (MCP server bridge), code-rag (RAG), prompt-store (prompt versioning).
T — Tie togetherMultiple workflows run in the background without you touching them. AI is your employee, not your tool.daily-agent (cron-driven orchestration) + agent-memory + llm-router (per-task model routing) + agent-replay (replay traces for debugging). The morning-briefing skill in daily-agent is the reference example.

The four words that show up in every AI meeting:

  • system prompts — the briefing you give the AI before it starts. Use skill-runtime to template and version them.
  • RAG (retrieval-augmented generation) — the AI answers from your data instead of guessing. Use code-rag.
  • MCP (model context protocol) — a USB port that lets the AI actually do things in your apps. Use tool-bridge.
  • fine-tuning — taking a general AI and training it for one specific job. Not in this stack yet; use OpenAI/Anthropic/together.ai endpoints directly.

Stack quintet on npm (all v1+, BYO-LLM, zero deps): agentfit → agentguard → agentsnap → agentvet → agentcast. Each one wraps a thin slice of the agent loop. Pick the one that matches the failure you keep hitting in production.

The rest

Archived originals and forks are indexed in data/repos.ndjson (one JSON record per line, 945 records total). Refresh with:

./scripts/refresh.sh

This rewrites data/repos.ndjson from the GitHub API so the index stays fresh.

Files

FilePurpose
README.mdHuman-facing index (this file)
CLAUDE.mdClaude Code context — loaded on every session
AGENTS.mdMultica / generic-agent context (symlink to CLAUDE.md)
.multica/skills/Starter Multica skills for cross-repo work
scripts/refresh.shRegenerate the repo index from the GitHub API
scripts/provision.shImport skills + create agents in your Multica workspace (idempotent)
data/repos.ndjsonRaw repo metadata — one JSON record per repo

License

MIT

Repository Health

This repository includes a dependency-free health check for core documentation, metadata, and CI wiring. Run it locally before publishing changes:

python3 scripts/check_repository_health.py

The same check runs in GitHub Actions on pushes and pull requests.

Ver o original no GitHub

Bom para

Relacionados