Search Packages

datachain

Data Memory: the operational data context layer for AI agents - typed, versioned datasets over images, video, docs and tables

memtomem

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

graphrefly

Reactive harness layer for agent workflows. Describe automations in plain language, trace every decision, enforce policies, persist checkpoints. Python. Zero dependencies.

browser-automation-cli

A lightweight, self-hosted browser automation tool with a background daemon and CLI client. Tailored for agent harnesses.

interlocks

One opinionated command surface for local checks and CI, replacing per-repo quality-script sprawl with a consistent, enforceable workflow.

tok-protocol

tok is an invisible bridge

kogwistar

Graph-native AI substrate for HyperGraphRAG. Knowledge, Workflow orchestration, conversation memory and wisdom are modeled as hypergraphs. Support strong event sourced provenance and replay.

carl-studio

Coherence-Aware Reinforcement Learning (CARL) - breakthrough LLM post-training and test-time training paradigm. carl builds the world's most advanced and intelligent agent systems that are a step change over current gen agents

superagentic-metaharness

Meta Harness Implementation

syrin

Python library for building AI agents with budget management, declarative definitions, and production-ready observability.

pantheon-agents

A general, evolvable, and distributed agent framework & harness for data science.

claude-md-compiler

Compile CLAUDE.md into a lockfile, then enforce repo changes against it in local runs, staged diffs, or CI.

ceo-py

A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.

harness0

Layer 0 of agent reliability — the framework-agnostic harness that makes any AI agent stable.

carl-core

Coherence-Aware Reinforcement Learning (CARL) - breakthrough LLM post-training and test-time training paradigm. carl builds the world's most advanced and intelligent agent systems that are a step change over current gen agents

adam-mcp

MCP server that exposes Adam Framework vault memory as tools for Claude Desktop, Cursor, and any MCP-compatible client

ctxtual

Context engineering library for AI agents: decorator-based workspace storage for large tool results

agent-slides

Agent skill for generating professional PowerPoint decks. 7 composable skills and a purpose-built CLI.

autono

A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.

hdd-dev

HDD: Harness-Driven Development — cross-artifact change impact analysis

graphrefly-py

Reactive harness layer for agent workflows. Describe automations in plain language, trace every decision, enforce policies, persist checkpoints. Python. Zero dependencies.