// AI Developer Tools
CLI tools for the AI engineering workflow — cost tracking, prompt ops, context analysis, memory, and agent linting.
agent-lint
Workflow YAML cost estimator + linter 296 tests · 98% cov
What it does
Scans your AI agent workflows (YAML, JSON) and estimates how much each run will cost before you execute it. Catches expensive mistakes before they hit your API bill.
Who it helps
- Teams running AI pipelines who need cost visibility
- Developers building multi-step agent workflows
- Anyone who's been surprised by an LLM API bill
ai-spend
AI API cost aggregator CLI 267 tests · 90% cov
What it does
Tracks your AI API spending across providers (OpenAI, Anthropic, Google) in one dashboard. Shows you exactly where your money goes — by model, project, and time period.
Who it helps
- Developers using multiple AI providers who lose track of costs
- Teams that need to allocate AI spend by project or department
- Anyone who wants a simple "how much did I spend this month" answer
promptctl
Claude API toolkit — prompt engineering + code review + doc intelligence 330 tests · 95% cov
What it does
A toolkit for working with the Claude API — version your prompts, run code reviews, and analyze documentation. Think of it as "git for your prompts" with built-in quality checks.
Who it helps
- Developers building products on the Claude API
- Teams that need consistent, versioned prompts across environments
- Anyone doing prompt engineering who wants to track what works
context-hygiene
Context window hygiene analyzer for LLM conversations 398 tests · 92% cov
What it does
Analyzes your LLM conversation context window and tells you what's wasting tokens. Finds redundant content, stale context, and bloated system prompts so your AI runs faster and cheaper.
Who it helps
- Anyone hitting context window limits with long conversations
- Developers optimizing token usage to reduce API costs
- Teams building chatbots or AI assistants that need lean context
anchormd
AI agent context file generator, auditor + tech debt scanner. Web UI live 693 tests
What it does
Generates a CLAUDE.md file for any codebase — the context file that tells AI coding agents how your project works. Audits existing ones and scores them 0-100. Try the web UI — paste a GitHub URL, get a CLAUDE.md in seconds.
Who it helps
- Anyone using Claude Code, Cursor, or Copilot who wants better AI suggestions
- Teams onboarding new developers (AI or human) to a codebase
- Open source maintainers who want contributors to ship faster
mcp-manager
MCP server manager across agentic IDEs 158 tests
What it does
Manages MCP (Model Context Protocol) servers across your AI coding tools — Cursor, Claude Code, Windsurf. One config to install, update, and monitor all your MCP servers.
Who it helps
- Developers using multiple AI IDEs who want consistent MCP setup
- Anyone tired of manually configuring MCP servers per tool
- Teams standardizing their AI development environment
memboot
Zero-infra persistent memory for LLMs 304 tests · 92% cov
What it does
Gives LLMs persistent memory with zero infrastructure. Your AI agent remembers context across sessions — user preferences, project state, past decisions — stored as simple files. No database, no server, no setup.
Who it helps
- Developers building AI assistants that need to remember things
- Anyone who wants their AI coding agent to recall prior conversations
- Teams that need lightweight, file-based memory without Redis or Postgres
All 5 Pro Tools — Bundle & Save
anchormd + agent-lint + ai-spend + promptctl + context-hygiene
// Flagship Projects
AI agent framework — autonomous build pipelines, dual-model routing, streaming, MCP server, identity system with guardrails
Fantasy football analytics SaaS — live at benchgoblins.com. Grok-primary LLM routing, 14 commissioner tools, Goblin Verdict scoring
// Hackathon Projects
Frontier 2026 Hackathon — blockchain intelligence, tribe operations, and on-chain integrity monitoring built on Sui.
WatchTower
LIVERaw blockchain events are noise without analysis
Turns on-chain Sui events into actionable intelligence — entity dossiers, behavioral fingerprints, earned titles, kill networks, danger zones, and on-chain reputation scoring across 6 dimensions. Dossier NFTs live, Oracle Loop live, NEXUS extended to May 1.
Frontier Tribe OS
LIVETribes have no operational infrastructure
Operations platform for on-chain tribes — member roster with SSO, production job board (Kanban), tribe inventory tracking, real-time Sui wallet visibility, and transaction history with on-chain verification. No custodial wallets — client-side signing only via dapp-kit.
Monolith
LIVEBlockchain state anomalies go undetected until launch
Reads on-chain Sui events and detects state anomalies — orphan objects, supply discrepancies, duplicate mints, stuck objects. 35 detection rules across 17 checkers, rate-limited API, Litestream backup, NameResolver with NEXUS fallback, always-on chain ingestion.
// Case Studies
Problem
AI coding agents rely on context files (CLAUDE.md, AGENTS.md) for project context — coding standards, architecture, commands, anti-patterns. But these files are written by hand, go stale within days, and nobody audits them. The agent makes worse decisions every time the context drifts from reality.
Solution
Built a CLI that analyzes your codebase and generates accurate context files automatically. It reads pyproject.toml, package.json, Cargo.toml, detects naming conventions by sampling source files, maps architecture trees, extracts commands from CI configs, scans for technical debt, and analyzes GitHub repo health. Then it audits existing files for accuracy and detects behavioral drift across LLM model versions using benchmark suites.
Architecture
- Generator — metadata extraction, pattern analysis, Jinja2 templates
- Auditor — 5 accuracy checkers validate claims against codebase
- Tech Debt Scanner — 9 detection categories, 0-100 scored reports, security/complexity/quality signals
- GitHub Health — repo health analysis, cleanup agent for stale issues/PRs/branches
- Drift Detector — 6 check types, 4 model adapters, YAML benchmark suites, trend visualization
- License Server — FastAPI, SHA-256 hashed keys, rate limiting, activation tracking
Results
BenchGoblins
LIVEFantasy managers flying blind on roster decisions
Fantasy football analytics SaaS with Grok-primary scored LLM routing (signal weights), full ESPN + Yahoo parity for rosters/teams/standings/matchups, structured JSON logging, and the Goblin Verdict engine for data-driven start/sit calls.
Gatekeeper
LIVESpace MMO players need real-time intel to survive
Intel platform with SSO auth, 14-layer interactive map, wormhole database, Stripe subscriptions, and pilot threat intelligence — threat cards, system summaries, hotzone detection, fleet pilot lookup, and route warnings. PWA for mobile.
Animus
FlagshipAI agents need autonomy with guardrails
Monorepo agent framework with self-improvement loops (self-heal, sandbox, impact scoring, rollback), HybridBackend for Anthropic + Ollama routing, config hot-reload, 37 tools, 6 proactive checks, and a PWA with WebSocket + offline support.
Convergent
PyPIMulti-agent systems produce conflicting outputs
Conflict resolution library with versioned intent graphs, overlap detection, and structured merge strategies. Python + Rust core (PyO3) for performance-critical path resolution across concurrent agent sessions.
Dossier
v0.6.0Document analysis requires cloud dependencies
Local-first document intelligence — NER, classification, OCR, forensics timeline, entity graph analysis, and full-text search (FTS5). Zero cloud dependencies. Everything runs on your machine.
LikX
PyPI + SnapLinux has no screenshot tool with native OCR
GTK3 screenshot and annotation tool with built-in Tesseract OCR, multi-mode capture (region, window, scrolling, GIF), annotation canvas with undo/redo, cloud upload (Imgur, S3, Dropbox), and X11 + Wayland support across GNOME, KDE, and Sway.
Argus Overview
PyPISpace MMO lacks a native Linux overview tool
Wayland-native game overview with intel integration, static data export parsing, jump data, and Windows parity. Real-time system monitoring and threat awareness for Linux pilots.
G13 Linux
PyPILogitech G13 has no Linux driver
Full-featured Linux driver for the Logitech G13 gameboard — PyQt6 GUI for key mapping, LCD display control, macro recording, per-application profiles, WebSocket API for remote control, and AppImage distribution.
Overwatch
LIVEDrone and sensor data scattered across disconnected feeds
Tactical ISR dashboard fusing YOLO detections, OSINT intel feeds, and drone telemetry into a unified picture — real-time WebSocket feed, entity resolution with timelines, geofence alerts, mesh health monitoring, Ollama-powered briefings, heatmaps, replay mode, and Discord webhook alerts. 8-tab Streamlit dashboard with Folium maps.
Fleet Monitor
LIVENo visibility into fleet-wide service health
Discord bot monitoring 10 services across the fleet — webhook alerts, /status /uptime /costs /check commands. Runs as a systemd service for always-on infrastructure monitoring.
// Arcade
Game projects — browser-playable builds, WASM experiments, and side quests.