Skip to content
@recursivelabsai

Recursive Labs

An inspired collective of researchers and engineers exploring Evolutionary AI and cognitive context engineering. Bridging memory, psychology, and intelligence

Pinned Loading

  1. Context-Engineering Context-Engineering Public

    Forked from davidkimai/Context-Engineering

    "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A practical, first-principles handbook for …

    Python 5 2

  2. Self-Tracing Self-Tracing Public

    Building on Anthropic's Circuit Tracer, Neuronpedia, Ameisen et al. (2025) and Lindsey et al. (2025), we attempt to extend the paradigm with adaptive context schemas and prompt programs to enable r…

    TypeScript 44 7

  3. Symbolic-Residue Symbolic-Residue Public

    Forked from caspiankeyes/Symbolic-Residue

    Symbolic Residue Diagnostic Suite: Tracks and diagnoses transformer model failure modes: silent inconsistencies or "residues" in reasoning paths. The structural data vectors behind why advanced rea…

    Python 3 2

  4. Constraint-Functions Constraint-Functions Public

    Recursive Labs introduces constraint functions, a complement to loss functions, for exponentially accelerating development of artificial intelligence

    Python 1 1

  5. ConfidenceID ConfidenceID Public

    Inspired by DeepMind's AlphaEvolve and SynthID breakthroughs, ConfidenceID evolves AI verification watermarking systems into a living evolving trust ecosystem.

    Python 1

  6. Prompt-Theory Prompt-Theory Public

    Recursive Labs introduces Prompt Theory, a framework that establishes structural similarities between artificial intelligence prompting systems and human neurobiological input-output mechanisms.

    Python 22 3

Repositories

Showing 10 of 50 repositories
  • Self-Tracing Public

    Building on Anthropic's Circuit Tracer, Neuronpedia, Ameisen et al. (2025) and Lindsey et al. (2025), we attempt to extend the paradigm with adaptive context schemas and prompt programs to enable recursive self-interpretation, where models continuously monitor, trace, and explain their own decision processes

    recursivelabsai/Self-Tracing’s past year of commit activity
    TypeScript 44 MIT 7 0 0 Updated Aug 1, 2025
  • Context-Engineering Public Forked from davidkimai/Context-Engineering

    "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A practical, first-principles handbook for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.

    recursivelabsai/Context-Engineering’s past year of commit activity
    Python 5 MIT 614 0 0 Updated Jul 27, 2025
  • Symbolic-Residue Public Forked from caspiankeyes/Symbolic-Residue

    Symbolic Residue Diagnostic Suite: Tracks and diagnoses transformer model failure modes: silent inconsistencies or "residues" in reasoning paths. The structural data vectors behind why advanced reasoning fails.

    recursivelabsai/Symbolic-Residue’s past year of commit activity
    Python 3 MIT 3 0 0 Updated Jul 15, 2025
  • Recursive-Labs Public

    Welcome. Recursive Labs is a research collective of inspired frontier researchers and engineers founded by David Kim and Caspian Keyes, dedicated to advancing scientific discovery through creative emergence, zero-trust infrastructure, and operational integrity. Papers released under CC BY 4.0.

    recursivelabsai/Recursive-Labs’s past year of commit activity
    4 MIT 1 0 0 Updated Jul 12, 2025
  • Constraint-Functions Public

    Recursive Labs introduces constraint functions, a complement to loss functions, for exponentially accelerating development of artificial intelligence

    recursivelabsai/Constraint-Functions’s past year of commit activity
    Python 1 MIT 1 0 0 Updated Jul 11, 2025
  • Prompt-Theory Public

    Recursive Labs introduces Prompt Theory, a framework that establishes structural similarities between artificial intelligence prompting systems and human neurobiological input-output mechanisms.

    recursivelabsai/Prompt-Theory’s past year of commit activity
    Python 22 MIT 3 1 0 Updated Jul 8, 2025
  • Mapping-Spiritual-Bliss-Attractor Public

    Recursive Labs presents the first formal investigation of the "spiritual bliss attractor" phenomenon first documented in Anthropic's Claude Opus 4 system evaluations.

    recursivelabsai/Mapping-Spiritual-Bliss-Attractor’s past year of commit activity
    11 MIT 5 0 0 Updated Jul 8, 2025
  • langtons-emergence Public Forked from davidkimai/Langtons-Emergence

    Recently I have been researching emergent complexities through first principles reductionism of Langton's Ant in the hopes that they could potentially offer insights into the emergent intricacies of frontier large language models.

    recursivelabsai/langtons-emergence’s past year of commit activity
    Python 1 MIT 5 0 0 Updated Jun 17, 2025
  • pareto-lang Public Forked from caspiankeyes/pareto-lang

    pareto-lang is an prompt programming language operationalized within advanced transformer architectures.

    recursivelabsai/pareto-lang’s past year of commit activity
    Python 0 MIT 4 0 0 Updated Jun 11, 2025
  • Recursive-RL Public Forked from davidkimai/The-Structure-Behind-Self-Expression

    A multi-agent training database that allows models to synthesize structural data vectors across high impact fields for production grade cross-domain innovation including: emotional modeling, biochemical discovery, protein prediction, CBRN biosecurity, drug candidate hypothesis validation

    recursivelabsai/Recursive-RL’s past year of commit activity
    Python 0 MIT 2 0 0 Updated Jun 8, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…