agentlog · Multi-agent, multi-device activity pool + project context layer
agentlog has two layers:
- Layer 1 — event pool: captures notable activity from all your AI agents (Claude Code, Codex, Cursor, Maestri, browser-use) across all your machines (Macs + VPS) into one normalized event pool, synced via a private GitHub repo.
- Layer 2 — project context: distills the pool into a per-project
AGENTS.md + CLAUDE.md + docs/agent-context/ snapshot, so any AI coding agent entering the project reads the same up-to-date state, decisions, and next steps.
Boundaries (when NOT to use)
| Task |
Use this instead |
| Capture a single Claude Code session for tweet drafting |
seed skill |
| One-off project planning / brainstorming |
planner / brainstorming |
| Team collaboration / sharing with others |
(not supported in v0) |
Architecture
┌─────────────────────────────────────────────────────────────┐
│ Device A (Mac) Device B (VPS) │
│ ───────────────── ───────────────── │
│ Claude Code Claude Code │
│ Codex Codex │
│ Maestri canvas (scripts) │
│ browser-use │
│ ↓ ↓ │
│ agentlog adapters agentlog adapters │
│ ↓ ↓ │
│ ~/.agent-seeds/ ~/.agent-seeds/ │
│ (local pool clone) (local pool clone) │
│ ↓ ↓ │
│ └──── GitHub (private repo) ────┘ │
└─────────────────────────────────────────────────────────────┘
Each agent → adapter → local pool shard → GitHub. Other devices pull. Everyone sees a unified feed.
Setup
Detailed: references/setup.md. Quick version:
gh repo create agent-seeds --private --confirm
agentlog init --repo git@github.com:YOUR_USER/agent-seeds.git
agentlog poll --once --source claude_code # smoke test
On each additional device: same agentlog init command. Pool syncs via GitHub.
Common flows
See what I did across all agents today
agentlog recap
Live feed of last 4 hours, all sources
agentlog pool --last 4h
Group view by project / agent / source
agentlog pool --by project
agentlog recap --by agent
Pull everything from other machines now
agentlog pull
Push current local changes immediately
agentlog push --force
Manually log an event from a script
agentlog event push '{"action":{"type":"checkpoint","status":"completed","label":"deploy success"},"summary":"shipped api v2"}'
Distill a project's recent activity into a context document (Layer 2)
agentlog context init --project-root .
agentlog brief --project agentlog --last 7d
Writes AGENTS.md + CLAUDE.md + docs/agent-context/{state,decisions,next-steps}.md so the next agent (Cursor / Codex / Claude Code) entering the project reads a unified state. Requires ANTHROPIC_API_KEY.
Re-sync entry-file blocks after manually editing state
agentlog context sync
Migrate historical seed data (one-time)
agentlog migrate-from-seed --dry-run
agentlog migrate-from-seed
Run the background daemon (auto poll + sync)
agentlog daemon install # macOS launchd or Linux systemd
agentlog daemon start
Reference index
| File |
Covers |
references/cheatsheet.md |
Start here — one-page mental model: commands, capture modes, push rhythm, file layout, schema |
references/setup.md |
Full multi-device install, GitHub remote, env vars, daemon install |
references/troubleshooting.md |
Common install / sync failures with root-cause + fix (UNKNOWN-0.0.0, command not found, SSH publickey, hostname collision, Cursor adapter blank) |
references/cli-reference.md |
Every CLI command with examples |
references/cursor-adapter.md |
Cursor IDE SQLite storage layout, action-type mapping, schema-drift handling |
references/brief.md |
Haiku distill prompt contract, event selection, idempotency rules |
references/context-contract.md |
AGENTS.md + CLAUDE.md double-write, decisions append-only, decision entry format |
For schema details read src/agentlog/schema.py directly — the type hints + validate() are the source of truth.
When extending
- Adding a new source → implement
SourceAdapter interface (src/agentlog/adapters/base.py), register in _ADAPTER_REGISTRY in src/agentlog/cli.py
- Changing event schema → bump
SCHEMA_VERSION in src/agentlog/schema.py and write a converter
- Adding a CLI command → wire into
build_parser() in src/agentlog/cli.py
Status
v0 — schema + pool + 5 adapters (claude_code, codex, cursor, maestri, browser_use) + GitHub sync + daemon + shot + recap + Layer 2 (brief + context). Tests: 59 passing.
1---2name: agentlog3description: Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT load for single-machine tweet material capture (use `seed`) or one-off project planning.4metadata:5 source: https://skillmd.com/skills/yrzhe/agentlog6---78# agentlog · Multi-agent, multi-device activity pool + project context layer910agentlog has two layers:1112- **Layer 1 — event pool**: captures notable activity from all your AI agents (Claude Code, Codex, Cursor, Maestri, browser-use) across all your machines (Macs + VPS) into one normalized event pool, synced via a private GitHub repo.13- **Layer 2 — project context**: distills the pool into a per-project `AGENTS.md` + `CLAUDE.md` + `docs/agent-context/` snapshot, so any AI coding agent entering the project reads the same up-to-date state, decisions, and next steps.1415## Boundaries (when NOT to use)1617| Task | Use this instead |18|---|---|19| Capture a single Claude Code session for tweet drafting | `seed` skill |20| One-off project planning / brainstorming | `planner` / `brainstorming` |21| Team collaboration / sharing with others | (not supported in v0) |2223## Architecture2425```26┌─────────────────────────────────────────────────────────────┐27│ Device A (Mac) Device B (VPS) │28│ ───────────────── ───────────────── │29│ Claude Code Claude Code │30│ Codex Codex │31│ Maestri canvas (scripts) │32│ browser-use │33│ ↓ ↓ │34│ agentlog adapters agentlog adapters │35│ ↓ ↓ │36│ ~/.agent-seeds/ ~/.agent-seeds/ │37│ (local pool clone) (local pool clone) │38│ ↓ ↓ │39│ └──── GitHub (private repo) ────┘ │40└─────────────────────────────────────────────────────────────┘41```4243Each agent → adapter → local pool shard → GitHub. Other devices pull. Everyone sees a unified feed.4445## Setup4647Detailed: `references/setup.md`. Quick version:4849```bash50gh repo create agent-seeds --private --confirm51agentlog init --repo git@github.com:YOUR_USER/agent-seeds.git52agentlog poll --once --source claude_code # smoke test53```5455On each additional device: same `agentlog init` command. Pool syncs via GitHub.5657## Common flows5859### See what I did across all agents today60```bash61agentlog recap62```6364### Live feed of last 4 hours, all sources65```bash66agentlog pool --last 4h67```6869### Group view by project / agent / source70```bash71agentlog pool --by project72agentlog recap --by agent73```7475### Pull everything from other machines now76```bash77agentlog pull78```7980### Push current local changes immediately81```bash82agentlog push --force83```8485### Manually log an event from a script86```bash87agentlog event push '{"action":{"type":"checkpoint","status":"completed","label":"deploy success"},"summary":"shipped api v2"}'88```8990### Distill a project's recent activity into a context document (Layer 2)91```bash92agentlog context init --project-root .93agentlog brief --project agentlog --last 7d94```95Writes `AGENTS.md` + `CLAUDE.md` + `docs/agent-context/{state,decisions,next-steps}.md` so the next agent (Cursor / Codex / Claude Code) entering the project reads a unified state. Requires `ANTHROPIC_API_KEY`.9697### Re-sync entry-file blocks after manually editing state98```bash99agentlog context sync100```101102### Migrate historical seed data (one-time)103```bash104agentlog migrate-from-seed --dry-run105agentlog migrate-from-seed106```107108### Run the background daemon (auto poll + sync)109```bash110agentlog daemon install # macOS launchd or Linux systemd111agentlog daemon start112```113114## Reference index115116| File | Covers |117|---|---|118| `references/cheatsheet.md` | **Start here** — one-page mental model: commands, capture modes, push rhythm, file layout, schema |119| `references/setup.md` | Full multi-device install, GitHub remote, env vars, daemon install |120| `references/troubleshooting.md` | Common install / sync failures with root-cause + fix (UNKNOWN-0.0.0, command not found, SSH publickey, hostname collision, Cursor adapter blank) |121| `references/cli-reference.md` | Every CLI command with examples |122| `references/cursor-adapter.md` | Cursor IDE SQLite storage layout, action-type mapping, schema-drift handling |123| `references/brief.md` | Haiku distill prompt contract, event selection, idempotency rules |124| `references/context-contract.md` | AGENTS.md + CLAUDE.md double-write, decisions append-only, decision entry format |125126For schema details read `src/agentlog/schema.py` directly — the type hints + validate() are the source of truth.127128## When extending129130- Adding a new source → implement `SourceAdapter` interface (`src/agentlog/adapters/base.py`), register in `_ADAPTER_REGISTRY` in `src/agentlog/cli.py`131- Changing event schema → bump `SCHEMA_VERSION` in `src/agentlog/schema.py` and write a converter132- Adding a CLI command → wire into `build_parser()` in `src/agentlog/cli.py`133134## Status135136v0 — schema + pool + 5 adapters (claude_code, codex, cursor, maestri, browser_use) + GitHub sync + daemon + shot + recap + Layer 2 (brief + context). Tests: 59 passing.