A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advanced capabilities like reasoning backtracking, latent thought optimization, and metacognitive control.
☆35Mar 22, 2026Updated 6 months ago
Alternatives and similar repositories for llm_introspective_compression_and_metacognition
Users that are interested in llm_introspective_compression_and_metacognition are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Network observer that tracks outbound connections from AI CLI processes (Claude Code, Codex, Gemini), attributing sockets to providers in…☆31Updated this week
- SDK-first orchestration platform for managing AI coding agent fleets: BYOA key rotation, real-time WebSocket dashboard, DCG integration, …☆23Updated this week
- Spec-first Rust port of TOON (a token-efficient data format): deterministic JSON<->TOON conversion with strict validation and streaming s…☆28Updated this week
- Memory-safe clean-room Redis reimplementation in Rust with strict/hardened compatibility modes, deterministic replication semantics, diff…☆27Updated this week
- Pitting together all the best LLMs to fight in a coding tournament with no holds barred! Who will win? You!☆15Mar 22, 2026Updated 6 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Public research about LLMs, Implied Cognition, experiments, tests, etc☆29Mar 19, 2023Updated 3 years ago
- Bayesian process classifier that detects abandoned/zombie processes and recommends safe cleanup actions☆28Updated this week
- Deep Networks Grok All the Time and Here is Why☆40Apr 20, 2026Updated 5 months ago
- A secure, zero-touch API provisioning protocol driven by contracts and powered by AI☆13May 4, 2025Updated last year
- Rust web framework inspired by Python's FastAPI: type-safe routing, zero-copy parsing, OpenAPI generation, and structured concurrency via…☆23Updated this week
- Trust-native JavaScript/TypeScript runtime platform built on franken_engine with deterministic compatibility, migration autopilot, extens…☆30Updated this week
- Autonomous, agentic, creative story writing system that incorporates stored embeddings and Knowledge Graphs.☆112Sep 15, 2026Updated last week
- Learn and explore the world of phages, the viruses that attack bacteria. A window into the world of genetics.☆28Updated this week
- Next-gen Rust diagram engine with 15 layout algorithms, deterministic output, intent-aware recovery, and WASM/SVG/Canvas/terminal rendere…☆52Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A Multi-Agentic AI Assistant/Builder☆28Jun 1, 2026Updated 3 months ago
- Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document proces…☆159Updated this week
- Easy to install Text to Speech system for Raspberry Pi 4☆18Mar 4, 2024Updated 2 years ago
- Running Microsoft's BitNet inference framework via FastAPI, Uvicorn and Docker.☆42Jul 2, 2025Updated last year
- Bridge Python and TypeScript with ease. Use simple decorators to expose Python functions, methods, and classes to TypeScript with full ty…☆23Mar 7, 2025Updated last year
- ☆35Jan 30, 2025Updated last year
- Code for "The Geometry of Concepts: Sparse Autoencoder Feature Structure"☆18Mar 25, 2025Updated last year
- CompChomper is a framework for measuring how LLMs perform at code completion.☆21Apr 29, 2025Updated last year
- Replayable Browser Agent☆17Apr 24, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Autonomous fiction engine — three agents publish a fictional Wikipedia. Hermes-4-70B (canon + critics) + Kimi-K2.6 (prose) + FLUX + Eleve…☆36May 2, 2026Updated 4 months ago
- AgentOS is a lightweight, single-file implementation that provides a robust foundation for building autonomous AI agents. It implements t…☆30Jul 11, 2025Updated last year
- A meta-framework for self-improving LLMs with transparent reasoning☆45Dec 10, 2025Updated 9 months ago
- Using experimental methods to merge large language models☆11Jul 11, 2026Updated 2 months ago
- Powered by ChatterboxTTS | Transformer | Llama | Gradio☆18Sep 7, 2025Updated last year
- Blue-text Bot AI. Uses Ollama + AppleScript☆50May 19, 2024Updated 2 years ago
- RAIL wireless applications. Go to https://github.com/SiliconLabs/application_examples☆13Jul 24, 2026Updated 2 months ago
- Context Hub Runtime Environment (CHRE)☆11Mar 13, 2026Updated 6 months ago
- Repo for solving arc problems with an Neural Cellular Automata☆27Mar 9, 2026Updated 6 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆21Jan 25, 2025Updated last year
- The implement of LLMTreeRec☆14Dec 9, 2024Updated last year
- Non-official implementation of "Attention as an RNN" from https://arxiv.org/pdf/2405.13956, efficient associative parallel prefix scan an…☆28Jul 27, 2024Updated 2 years ago
- Native macOS control panel for Clawdbot☆15Mar 12, 2026Updated 6 months ago
- Reference implementation of models from Nyonic Model Factory☆12May 13, 2024Updated 2 years ago
- Official PyTorch implementation of CD-MOE☆12Mar 18, 2026Updated 6 months ago
- LLMEval☆11Feb 12, 2024Updated 2 years ago