Explore

Governed single-operator data fabric for agents and dashboards

Python·Apache-2.0·Few stars·No key

Every git worktree gets its own isolated local world — ports, env, a database slice, and URLs. One `binky up` per branch.

Python·Apache-2.0·★ 1·Few stars·No key

A task queue whose only infrastructure is PostgreSQL: SKIP LOCKED claims, asyncio workers, schedules, webhooks, and an optional FastAPI HTTP/MCP API with JWT auth and a web UI.

Python·MIT·Few stars·No key

Privacy-first WeChat archive MCP plugin and Agent Skill for DeepSeek Harness | 本地优先、默认拒绝危险状态的微信归档插件

Python·MIT·Few stars·No key

Local automation platform with a web dashboard for managing scheduled Python/batch tasks. Flask backend, Redis workers, APScheduler, SQLite persistence, live debug log. No terminal required after laun

Python·MIT·Few stars·No key

End-to-end algo trading workbench: data collection → research → strategy → execution. Crypto (Alpaca) + futures (IBKR), Neo4j research provenance graph, prop-firm-style risk engine.

Python·MIT·★ 1·Few stars·No key

search a codebase by what the code does, not the words in it. tree-sitter chunking, hybrid vector + bm25 retrieval, one sqlite file, offline.

Python·MIT·Few stars·No key

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

Skill·MIT·★ 49·No key

The recorder for your AI conversations — local-first MCP memory that keeps byte-exact copies of your Claude Code, Codex and Pi sessions (Claude Code deletes its own after 30 days) and answers with a c

Python·MIT·★ 81·No key

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever - even when the API is down.

Python·MIT·★ 9·No key

Persistent memory and knowledge graph for AI agents via MCP — PostgreSQL + pgvector + Ollama

Python·MIT·★ 1·Few stars·No key

RAG for researchers: page-level citations from your personal library, LLM access via MCP. Ask your entire archive, get answers with the intelligence of leading AI.

Python·MIT·★ 9·No key

The memory database for AI agents. One recall primitive: intent in, the right context out (hybrid retrieval, token-budget packing, in-engine lifecycle, bitemporal audit, per-tenant RLS). MCP-native. O

Python·Apache-2.0·★ 3·Few stars·No key

CLI and TUI that aggregates CS internships from 1,450+ employer boards into a local SQLite database. Filters 146,000+ postings, sends Discord alerts, and works on macOS, Linux, and Windows.

Python·MIT·★ 2·Few stars·No key

Local-first AI memory: archive Claude Code, Codex, Claude desktop and Pieces history, search it over MCP, and explore it in the Memory Atlas.

Python·MIT·★ 6·No key

Agent OS Kernel: Bringing 50 years of OS wisdom to AI Agent infrastructure.Like Linux for AI Agents. Maps LLM→CPU, Context→RAM, Database→Disk. Features: intelligent context swapping, priority scheduli

Python·MIT·★ 3·Few stars·No key

Local-first persistent memory for AI agents — store, recall, and consolidate knowledge across sessions using FAISS, SQLite, and any LLM. MCP server for coding agents and any MCP client.

Python·MIT·★ 7·No key

Local MCP coordination layer for multi-agent coding: task leases, auditable handoffs, independent acceptance contracts.

Python·MIT·★ 1·Few stars·No key

MCP server for SQL Server tuning, diagnostics, and performance analysis

Python·MIT·★ 2·Few stars·No key

Unofficial local Windows tray + CLI to repair, clean up and safely maintain the OpenAI Codex desktop app

Python·MIT·★ 1·Few stars·No key

Autonomous AI organizations, persistent digital workforce, and time-compressed world simulation. Features enforceable role contracts, task DAGs, independent audits, decision trees, and native MCP stdi

Python·Apache-2.0·★ 1·Few stars·No key

Temporal memory for your AI agents, financial research, and knowledge workflows.

Python·MIT·★ 5·No key