Havuz

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

Python toolkit for PowerPoint ↔ HTML, built for AI. Round-trip fidelity preserves formatting across every edit loop — ideal for RAG ingestio

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.

Swap, lend, trade perps, add liquidity, move SOL, read the market. One binary your agent calls, across every venue.

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

The agent that evolves with you 𖤍

Skill to generate the knowledge vault for projects using the Ralph loop

Let Claude Code, Codex and Pi talk to each other: cross-session messaging that wakes AI agents on one machine or across your LAN (macOS/Linu

Your coding agents forget. Graft doesn't. Persistent local memory that brings back fixes, decisions and project knowledge when they matter —

An opinionated and efficient automated software-factory

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows,

A local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the da

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

Stateful execution layer for browser agents.

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact out

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before t

Let Claude run code on your real machine — safely — from any Claude chat. Bridges Claude Cowork to Claude Code on your Mac/Linux box. One co

Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.