Flint compiles compact, human-editable chart specs into polished Vega-Lite, ECharts, or Chart.js visualizations so agents and developers can skip hand-tuning scales, axes, and spacing.
Agents
underdogs · picking up speedThis PowerShell-heavy repo turns Claude Code and friends into a guided missile for APK analysis, CTFs, and binary diffing—if you can survive the bootstrap ritual.
Raven wraps agents in durable memory and self-refining skills so workflows survive past the chat session.
A hybrid CLI tool that uses deterministic pipelines to keep LLM agents from drifting off-target during code review.
Most AI scientist tools are monolithic prompt pipelines; FAROS treats research automation as a composable runtime problem rather than a single-agent stack.
It replaces flat vector dumps with a four-tier semantic pyramid and Mermaid symbol graphs so agents remember workflows without drowning in their own tool logs.
ego lite is a macOS browser that isolates AI agents in parallel Spaces so they can automate the web with your real logins while your tabs stay untouched.
This fork rebuilds a popular multi-agent trading framework for the A-share market, replacing Yahoo Finance with free local data feeds and adding analysts who track policy shifts, hot-money flows, and lockup expirations instead of just fundamentals.
A self-hostable infinite canvas that wires AI image generation, reference editing, and chat into one collaborative workspace.
It wraps your operating system's accessibility APIs into an MCP server so any AI agent can see and control your desktop without waiting for OpenAI's closed beta.
A set of engineering rituals that stop stateless AI agents from confidently building the wrong thing by forcing them to think first.
Born from a $400/month Claude bill and nondeterministic merges, Bernstein orchestrates parallel CLI agents with deterministic scheduling and a tamper-evident audit trail.
Memora is an MCP server that stores agent outputs in a durable, semantically searchable knowledge graph so AI assistants can recall context across sessions.
Eta turns Xiaomi and OPPO phones into hosts for a system-level AI agent that controls devices through structured APIs, GUI automation, and root shells instead of blindly tapping buttons.
Codeman wraps AI coding CLIs in a self-hosted web dashboard so you can manage long-running agents from your phone without fighting lag or tiny keyboards.
Octop gives households and small teams a private AI assistant platform where every conversation and credential stays on your own machine.
It chains a dozen LLM agents into a visual workflow so your on-call engineer only has to tap 'approve' instead of SSHing in at 3 AM.
A Python layer that makes AI agents explain themselves through structured context graphs, decision trails, and W3C-compliant provenance.
It replaces manual GitHub hunts and markdown copying with a searchable, one-click installer for skills across 20+ AI agents.
A standalone Rust agent that edits Unity projects from the outside, because living inside the editor would make most of its features technically impossible.



