Updated 2w ago
by 7df-lab
devo
A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.
344 GitHub stars (344)
+21 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | 0 |
| Oct 4 | +1 |
| Oct 5 | 0 |
| Oct 6 | −1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | −1 |
| Oct 11 | +1 |
| Oct 12 | 0 |
| Oct 13 | −1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | −1 |
| Oct 17 | +14 |
| Oct 18 | 0 |
| Oct 19 | +2 |
| Oct 20 | +4 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | 0 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | +1 |
| Nov 3 | +2 |
| Nov 4 | 0 |
| Nov 5 | 0 |
- 15 skills (15 skills found in its SKILL.md files)
- 139 forks (139 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add 7df-lab/devo
Asks which skills and agents to install. Just one: npx skills add 7df-lab/devo --skill agent_observe — add -g for every project.
Claude Code
git clone https://github.com/7df-lab/devocp -r "devo/crates/core/rlm_skills/agent_observe" ~/.claude/skills/
Copies the agent_observe skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add 7df-lab/devo
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
agent_observe
Observe nuclear-family agents (self, parent, siblings, children) from the Python REPL. Use to list related sessions, inspect one agent, or read recent message previews.
crates/core/ on GitHub (opens in a new tab)rlm_skills/ agent_observe/ SKILL.md -
compact
Check context usage and compact the conversation from the Python REPL. Use when context is filling up, so the session is summarized and context is freed for the next stretch of work.
crates/core/ on GitHub (opens in a new tab)rlm_skills/ compact/ SKILL.md -
goal
Manage the persistent thread goal from the Python REPL. Use to read goal status and budget usage, to start a goal when the user explicitly asks for one, or to mark the active goal complete once its objective is fully achieved.
crates/core/ on GitHub (opens in a new tab)rlm_skills/ goal/ SKILL.md -
refine
Continual harness refinement (prompt notes, memory, skills, subagents). Schedule `await refine.run(...)` / `await refine.status()`; apply happens at turn boundary.
crates/core/ on GitHub (opens in a new tab)rlm_skills/ refine/ SKILL.md -
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.
crates/server/ on GitHub (opens in a new tab)skills/ .system/ skill-creator/ SKILL.md -
skill-installer
Install the agent skills into $DEVO_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
crates/server/ on GitHub (opens in a new tab)skills/ .system/ skill-installer/ SKILL.md -
agent-message
Message an agent's parent, siblings, or direct children through the daemon. Discover reachable agents with agent_observe.list_agents, then send direct text without spoofing sender identity.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ agent-message/ SKILL.md -
agent-observe
Read-only roster and observation of an agent's parent, siblings, and direct children. Use to discover reachable agents and to inspect family status and bounded recent-message previews without mutating sessions.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ agent-observe/ SKILL.md -
attach-image
Load an on-disk image (PNG, JPEG, GIF, WebP) into the model's context as a viewable attachment so the model can directly SEE it — for screenshots, diagrams, charts, photos, or scanned pages. Use this when you need to perceive an image's visual contents. Requires a vision-capable model; errors clearly otherwise.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ attach-image/ SKILL.md -
edit
Replace an exact, unique string in an existing file. Use for targeted single-occurrence edits to files from the Python kernel instead of rewriting the whole file.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ edit/ SKILL.md -
linear
Read and write Linear issues, projects, cycles, comments, and more via Linear's official MCP server. Tools are auto-discovered from the server at runtime.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ linear/ SKILL.md -
notion
Search Notion and read/create/update pages and databases via Notion's official hosted MCP server. Tools are auto-discovered from the server at runtime.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ notion/ SKILL.md -
rlm-heartbeat
Manage agent-owned RLM heartbeats from the Python REPL. Use when the user asks the agent to start, create, schedule, or manage a heartbeat, unless they explicitly request the user's /heartbeat.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ rlm-heartbeat/ SKILL.md -
websearch
Search the web. Prefer Devo hosted web_search (provider-hosted tool or local Exa/Tavily). Fall back to Serper only when hosted search is unavailable. Use when the user asks to search the web and no web_search tool is already available.
crates/skills/ on GitHub (opens in a new tab)assets/ bundled/ websearch/ SKILL.md -
deep-research
Use when a question requires deep investigation using online information or web search, broad source-backed research, comparison of multiple perspectives, or synthesis beyond a quick lookup.
crates/skills/ on GitHub (opens in a new tab)src/ assets/ samples/ deep-research/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.