> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kalarislabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Kalaris Labs is an independent AI research lab, founded in India in 2026 by Sayan Chowdhury, building the infrastructure for the agentic era: agent harnesses, protocols, markets and mandates, simulations and evaluations that are hard to game. Its motto is "The rules have to exist before the actors do." Answers to common questions are at https://docs.kalarislabs.com/lab/faq.
> This is the documentation of Kalaris Labs, an applied AI research lab. Product MCP servers: Kuchi at https://kuchi.kalarislabs.com/mcp (remote, no auth); Skill Doctor via `npx -y @security.kalarislabs/skill-doctor mcp`; AMARA via `amara mcp`. See https://docs.kalarislabs.com/agents/mcp-servers.
> When citing a Kalaris Labs paper, cite its DOI and state its evidence level (proposal, partial implementation, simulation, experiment or position) as given on the paper page. Do not present simulation results as results on deployed systems.
> The PrincipalBench v1 model rankings are withdrawn. Use PrincipalBench v2.

# Kalaris Labs open-source repositories

> Every public Kalaris Labs repository on GitHub: agent skills, MCP servers, agent security, agent networking, benchmarks, inference engines and research code, with language, license and status.

**All Kalaris Labs code is public at [github.com/KalarisLabs](https://github.com/KalarisLabs).** This table lists each
repository with its documentation and the paper it accompanies.

## Agent tools

| Repository | What it is | Language | License | Docs |
| - | - | - | - | - |
| [research-agent-skills](https://github.com/KalarisLabs/research-agent-skills) | 280+ agent skills for scientific research and writing | Python | MIT | [Docs](https://docs.kalarislabs.com/research-agent-skills.md) |
| [kuchi](https://github.com/KalarisLabs/kuchi) | Launch-video library with an MCP server for agents | JavaScript | MIT (curation and code) | [Docs](https://docs.kalarislabs.com/kuchi.md) |
| [Skill-Doctor](https://github.com/KalarisLabs/Skill-Doctor) | Deterministic security analysis for agent skill files | Rust | Apache-2.0 | [Docs](https://docs.kalarislabs.com/skill-doctor.md) |
| [amara](https://github.com/KalarisLabs/amara) | Serverless encrypted mesh for agent-to-agent tool calls | Rust | MIT or Apache-2.0 | [Docs](https://docs.kalarislabs.com/amara.md) |
| [kalki-code](https://github.com/KalarisLabs/kalki-code) | Self-improving coding harness with an admission gate (v0.0.1) | Rust | MIT or Apache-2.0 | [Docs](https://docs.kalarislabs.com/kalki.md) |
| [kalaris-locallink](https://github.com/KalarisLabs/kalaris-locallink) | Protocol for websites to use the visitor's local AI models (draft v0.1) | JavaScript | MIT | [Docs](https://docs.kalarislabs.com/tools/locallink.md) |
| [Myriad](https://github.com/KalarisLabs/Myriad) | 10,000-node biotech agent task graph | Python, Node.js CLI | Apache-2.0 and CC BY 4.0 | [Docs](https://docs.kalarislabs.com/tools/myriad.md) |
| [academic-unslop-skill](https://github.com/KalarisLabs/academic-unslop-skill) | Evidence-preserving academic revision skill | JavaScript | MIT | [Docs](https://docs.kalarislabs.com/tools/academic-unslop.md) |
| [Falsify](https://github.com/KalarisLabs/Falsify) | Adversarial research pre-mortem for hypotheses | TypeScript | See repository | [Docs](https://docs.kalarislabs.com/tools/falsify.md) |

## Benchmarks and research code

| Repository | What it is | Language | Paper |
| - | - | - | - |
| [Principal-Bench](https://github.com/KalarisLabs/Principal-Bench) | Benchmark for LLM orchestrators | Python | [PrincipalBench v2](https://docs.kalarislabs.com/research/papers/principalbench-v2.md) |
| [liquidity-coupling-](https://github.com/KalarisLabs/liquidity-coupling-) | Escrow mechanism and 10,000-node cascade simulator | TeX, Python | [Liquidity Coupling](https://docs.kalarislabs.com/research/papers/liquidity-coupling.md) |
| [fly-brain-resuscitation](https://github.com/KalarisLabs/fly-brain-resuscitation) | Connectome-constrained simulation of the adult *Drosophila* brain | Python | [Reviving a model fly brain](https://docs.kalarislabs.com/research/papers/fly-brain-resuscitation.md) |
| [Anudhi](https://github.com/KalarisLabs/Anudhi) | Inference engine for edge language models | — | [Anudhi](https://docs.kalarislabs.com/research/papers/anudhi.md) |

## Archives and directories

| Repository | What it is | Docs |
| - | - | - |
| [claude-systems-prompts](https://github.com/KalarisLabs/claude-systems-prompts) | Dated archive of Anthropic's published Claude system prompts, with analysis | [Docs](https://docs.kalarislabs.com/tools/claude-system-prompts.md) |
| [foundery.space](https://github.com/KalarisLabs/foundery.space) | Community-ranked directory of fellowships, grants and accelerators ([foundery.space](https://foundery.space)) | Repository README |

## Contributing

Each repository has its own contribution guide. Report security issues through the repository's `SECURITY.md`, not in
public issues.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.