# codejunkie99/agentic-stack

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

Repository: https://github.com/codejunkie99/agentic-stack
Canonical: https://ross.abutalabs.com/products/agentic-stack
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-06T23:32:59+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 96, longevity 10
- inputs: {"age_days": 140, "days_push": 27, "days_rel": 27, "gap_med": 0, "n_releases_24m": 22}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2238, forks 274 (observed 2026-08-28T04:06:29.446246+00:00)

## What it is
A Python-based framework providing a portable .agent/ folder of memory, skills, and protocols that plugs into many coding-agent harnesses (Claude Code, Cursor, Windsurf, Gemini CLI, DIY Python loops) and persists knowledge across tool switches. It also includes a local data layer for monitoring agent activity, costs, and KPIs, plus tooling to turn approved runs into eval cases and training-ready JSONL artifacts.

## Use cases
- keep agent memory when switching from cursor to claude code
- share skills and protocols across multiple coding agents
- run bounded agentic loops with budgets and checkpoints
- monitor token costs and agent activity locally
- build eval cases from approved agent runs
- manage cron-scheduled agent runs from one dashboard

## When to choose
- you use multiple coding-agent harnesses and want one shared memory/skills layer
- you need bounded, auditable agentic loops with resumable checkpoints
- you want local-first monitoring and eval artifacts without telemetry

## When to avoid
- you use a single agent harness and don't need portability
- you need OS-level sandboxing rather than supervisor-bounded loops
- you want a fully managed cloud agent platform

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, prompt-engineering, developer-tools, cli, monitoring, workflow-automation
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: portable-agent-memory, coding-agents, agent-harnesses, skills-folder, agentic-loops, claude-code, cursor, local-first, eval-flywheel, ai-agents, automation, command-line

## Member repositories
- codejunkie99/agentic-stack (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.446246+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:13.300985+00:00, confidence not recorded.
  - readme: https://github.com/codejunkie99/agentic-stack (fetched 2026-08-28T04:06:29.446246+00:00, sha b352cfa03eea)
- Data as of 2026-08-30T08:39:29.467469+00:00.