whereismyai
SLCR
SLCR is an open standard for writing software requirements documents that agents can read in slices and tools can check.
SLCR provides a standard format for writing software requirements documents using JSON, TOML, or YAML. It solves the problem of long prose specifications causing context rot and compounding agent errors by letting teams break requirements into sliceable, linked, and checkable parts. Requirements can refine and depend on each other while combining with logical operators. Acceptance criteria map directly to validators such as tests, linters, and agent checks. The reference implementation includes a CLI written in Rust and an agent skill that teaches agents to write requirements and use the tool.
SLCR at a glance
- Best for: Software engineer
- Runs on: CLI
- Pricing: Free
- Released: October 2026
- Category: AI coding tool
- Website: slcr.dev
Key features
- Sliceable requirements for agent contexts
- Linked requirements with logical operators
- Checkable acceptance criteria
- Support for JSON, TOML, and YAML formats
- Validator attachment to tests and linters
- CI integration for requirement checking
Use it for
- Writing software requirements for AI agents
- Checking requirement satisfaction with automated tools
- Structuring specifications to avoid context rot
Alternatives to SLCR
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Llmll — The compiler proves each function against its contract with Z3 before merging.
- Lcc — Cuts token counts significantly without losing exact session details.
- LangChain — Compose exactly the agent your use case needs from model, tools, prompt, and middleware.
- Velu — Evaluates documentation across 23 checks and 7 categories in seconds without a signup.
- Ellipsis — Manage custom coding agents via repo configuration files and automated infrastructure.
- Crit — It keeps human feedback localized and precise for AI agent code iterations.
- llmware — Build private, local RAG pipelines with 300+ prepackaged models and integrated document parsing.
- Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
- LLMSchema — Provides AI coding agents with accurate database schemas without context bloat.
- Go Modern Guidelines — Ensures AI agents write modern Go code instead of outdated patterns.
- OpenClaude — Connects one terminal interface to over 200 different AI models.
All SLCR alternatives