Search

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file.

Flexible type system for Ruby with coercions and constraints

Gokart solves reproducibility, task dependencies, constraints of good code, and ease of use for Machine Learning Pipeline.

Lightweight dynamic memory manager library for embedded systems with memory constraints. It implements malloc, calloc, realloc and free functions

An Entity Framework Core plugin to automatically add check constraints in various situations

Query language for blending SQL and local language models across structured + unstructured data, with type constraints.

Controlled text generation with programmable constraints

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.

Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evide

A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.

The Clash core builds on mihomo and is adapted to the constraints of Apple’s NetworkExtension framework. It processes traffic on your device, with performance tested on real hardware and the full source code open for review.

Solana-native verifiable compute and oracle protocol. Programs accept a job, an input, constraints, and a callback. Randomness is the first job. An active node can fulfill a VRF request with an ECVRF proof after it locks the configured stake and sends a heartbeat. Fees still do not move.

Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.