by ztratar · MCP Server · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Your private, searchable work timeline for macOS and local AI agents.
| Stars | 60 |
| Forks | 2 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 52.0772552277912/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-20 |
| Created | 2026-08-16 |
| Platforms | mcp, node |
| Est. Tokens | ~13k |
These tools work well together with openhistory for enhanced workflows:
Looking for a openhistory alternative? If you're comparing openhistory with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.
A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Local-first LLM proxy that meters what every agent run costs and kills runaways before they drain your budget.
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
Open-source MCP gateway and control plane for teams to govern which tools agents can use, what they can do, an
Explore other popular mcp server tools:
openhistory is Your private, searchable work timeline for macOS and local AI agents.. It is categorized as a MCP Server with 60 GitHub stars.
openhistory is primarily written in TypeScript. It covers topics such as activity-tracking, ai-agents, electron.
You can find installation instructions and usage details in the openhistory GitHub repository at github.com/ztratar/openhistory. The project has 60 stars and 2 forks, indicating an active community.
openhistory is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to openhistory on Agent Skills Hub include TaskWing, mcp-gearbox, maestro. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: