whereismyai
Manifestack
Manifestack is an open-source stack audit tool that runs inside coding agents to check project architecture and services.
Manifestack operates inside coding agents like Claude Code, Cursor, and Codex to audit your entire product stack, including frontend, backend, workers, infrastructure, and third-party APIs. It helps developers, small teams, and agencies select and maintain stacks by checking new services against project requirements, budgets, and data rules. The tool reads dependency files such as package.json, requirements.txt, pyproject.toml, Pipfile, and go.mod, but never modifies code or writes outside the .manifestack/ directory. It runs locally without requiring API keys or accounts, extracting public vendor pricing and limits to project future costs and bottlenecks. Built for projects from initial commit to hundreds of thousands of users, it generates findings on requirements, overlaps, overbuilt services, limits, bills, and risks.
Manifestack at a glance
Key features
- Audits projects inside coding agents
- Checks new vendor additions automatically
- Proposes stacks for specific budgets and user counts
- Reads multiple dependency and configuration formats
- Writes only to the .manifestack/ folder
- Runs locally without accounts or API keys
- Reports limits, bills, overlaps, and risks
Use it for
- Picking a stack for new projects based on budget and user count
- Checking new services added by coding agents before reliance
- Auditing existing repositories for vendor overlaps and limits
- Estimating upcoming bills and usage tier constraints
Alternatives to Manifestack
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- CodeScan Artex — It uses multiple parallel AI agents to read source code and verify vulnerabilities.
- SkillTotal — Scans code locally without accounts, telemetry, API tokens or executing the files.
- DeepAudit — Multi-agent architecture and sandbox PoC verification reduce false positives.
- ccusage — Tracks token usage and costs locally across multiple coding agent CLIs.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Gauge CLI — Runs real coding agents locally to find where they get stuck in your product.
- DeepSeek Harness — Builds on a plugin architecture to organize documents, analyze tables, and write code.
- Codacy — Enforces unified coding standards and security policies across the software lifecycle.
- Sonah — Verifies agent tasks and decisions against the actual code changes.
- Anti Samcheonpo — Catches redundant AI tasks and blocks wasted agent spending.
All Manifestack alternatives