TokRepo - Where AI Experience Lives
Infrastructure for the AI era. Manage your skills, MCPs, prompts and scripts in one place — humans confirm intent, agents install or push through TokRepo tools.
Connect TokRepo through MCP or CLI so any capable agent can search, evaluate, plan, install, and push assets through TokRepo.
Agents call TokRepo tools directly
Search, detail, verify, install-plan, and push flows are structured contracts for MCP/CLI agents; the web page only hands off the contract.
tokrepo_search(query)tokrepo_detail(uuid)tokrepo_verify(uuid)tokrepo_install_plan(uuid)Standalone gems — hand-picked, refreshed every 4 hours
Author just shipped an update — back on the radar.
Worth a look in this round.
Surfacing this one this cycle.
Picked out of the pile this window.
One to check this time around.
Seven verified assets for agent operations: runtime surfaces, orchestration harnesses, eval layers, and human-in-the-loop web control.
- ▸Hermes Agent — Self-Improving Multi-Channel AI Agent
- ▸Coze Loop — Agent Prompt, Eval, and Observability Hub
- ▸Giskard Checks — Evals and Safety Tests for LLM Agents
Ten verified database MCP servers and memory layers to query Postgres, MongoDB, ClickHouse, BigQuery, Trino, and dbt assets with guardrails.
- ▸Postgres MCP Pro — Index Tuning + Safe SQL Tools
- ▸pgEdge Postgres MCP — Read-Only by Default + Web UI
- ▸MongoDB MCP Server — npx + Read-Only Safety by Default
Seven GitHub-verified picks for auditable coding-agent operations: session capture, multiplexer control, self-improving context, rule sync, approvals, and policy verification.
- ▸Entire CLI — Git-Native AI Session Capture
- ▸herdr — Terminal Multiplexer for Coding Agents
- ▸AutoContext — Self-Improving Agent Harness
A practical 8-item stack to build safer agents: MCP registry + Kafka tools, installable skill packs, a Claude Code guide MCP, and reproducible data/RAG pipelines.
- ▸ToolSDK MCP Registry — Private Gateway + Sandbox
- ▸Confluent MCP — Kafka + Flink Tools via MCP
- ▸MCP Toolbox Python SDKs — Use Toolbox Tools in Apps
Promoted pack: generate scoped skills, keep CLAUDE/AGENTS docs in sync, manage MCP configs safely, and measure token budgets before agents read a repo.
- ▸aspens — Scoped Skills from Your Import Graph
- ▸MDA — Compile One Doc into SKILL/AGENTS/CLAUDE
- ▸agentrules — Multi-Provider AGENTS.md Generator
Six GitHub-verified building blocks to standardize agent skills, add persistent memory, and instrument runs end-to-end for measurable iteration.
- ▸MCP Memory Service — Persistent Agent Memory API
- ▸ToolHive — Run & Manage MCP Servers with thv
- ▸Skill Seekers — Convert Docs/Repos/PDFs to Skills