💎 React component to build layouts based on the CSS Flexbox model.
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
Reflexion with redux state manager
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
Architecture Decision Records with teeth — lifecycle management, 15 architecture paradigms, DDD context scoping, DCAR forces evaluation, reflexion models, Wardley mapping, C4 diagrams, ATAM tradeoff analysis, and 19 specialized agents for Claude Code.
Utils for read or write value into an object by string array with property names as items
Reasoning strategies for Reactive Agents — ReAct, Plan-Execute, and Tree-of-Thought
Prompt management for Reactive Agents — template engine and built-in prompt library
Agent deployment contracts — typed pacts for execution mode, budget, output, and scope
The composable AI agent framework built on Effect-TS — install everything with one package
See through your agent's decisions. React components for debugging agentfootprint runs — messages, prompts, tool calls, decision scope, cost.
YH-UI AI SDK integration for Vercel AI SDK and LangChain
AgentDB with optimized ONNX embeddings - 100% local, GPU-accelerated AI agent memory
Model Context Protocol server for agentic robotics with AgentDB integration
HeartFlow - AI Psychological Perception System
Proof-first Pi extension that uses a red-green-refactor cycle when behavior should be specified in tests first, with built-in parsing for popular test frameworks. Renamed from pi-proof; old name deprecated.
A Server-Driven UI (SDUI) component library for React
Continuous learning MCP server for Claude Code — observe patterns, reflect on them, evolve your workflow
Agent-first CLI for Universidad Norbert Wiener student portals (intranet ASP + Canvas LMS). Surfaces what the Wiener UI hides.
A lightweight framework for fact-checking AI-generated content.
Ｄｏｗｎｌｏａｄ ｅｂｏｏｋ ｐｄｆ ｍｏｂｉ ｅｐｕｂ Anthony Bourdain Appetites is available now
<a name="readme-top"></a>
<a name="readme-top"></a>
DSPy.ts 2.0 - Advanced declarative AI framework with multi-agent orchestration, self-learning capabilities, and state-of-the-art optimizers. Powered by AgentDB, ReasoningBank, and Swarm architecture.
Agent, Loop trait, ReactLoop, ConversationLoop, and run_reflexion for open-harness
Advanced vector database with ruvector integration for agent storage and skill management
Critic / Reflector traits, composition, and shipped impls for open-harness
Advanced cognitive pipelines for Ambi: RAG, Chain-of-Thought, Tree-of-Thoughts, and Reflexion.
AXON — the formal cognitive language: a deterministic, proof-carrying AI runtime. Native Rust lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the runtime: typed channels (π-calculus mobility, capability extrusion), algebraic effects via Free Monad CPS handlers, lease kernel + reconcile loop, the Epistemic Security Kernel, Trust Types, Proof-Carrying Code (independently verifiable proof objects), and the closed-catalog extension mechanism. Crate publishes as `axon-lang`; library import is `use axon::*` so existing call sites keep working unchanged.
Layer 3 reasoning — plan/output parsers + provider-agnostic local-inference scorers (router, complexity, relevance, retrieval, strategy, summariser, validator, entity enhancer) for the Brainwires Agent Framework
SQLite-based persistence layer for ExoGenesis Omega with schema migrations and transactions
Pluggable 3D memory extension for Ambi: KV state, semantic vector recall, and rolling summary.
Agent coordination primitives + multi-agent patterns for the Brainwires Agent Framework — communication hub, file/resource locks, task manager/queue, git coordination, contract net, saga, optimistic concurrency, market allocation, workflow graph, three-state model. LLM-driven workhorses live in `brainwires-inference`.
Console command to crypt and decrypt texts using classic methods.
CPU Monte Carlo photon tracer for virtual goniophotometry
A dot file parser
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.