CLI
Menu

Project management is context management.

For any agent, task or workflow: keep context, goals, tasks, decisions, evidence and memory in one shared record with full history. Typed items hold status and acceptance criteria; agents read them in compact TOON through one CLI and SDK. Use a plain folder, a hosted workspace or sync with your team’s tools. With or without git.

Coding, research, operations, long-running workflows and recursive agents that call themselves: the same record keeps the work in context.

Install pm

npm install -g @unbrained/pm-cli

Read the quickstart

One record, every changepm-0682l4

pm-0682l4 · Issue · P0

GH-827: local package install must prevent recursive self-copy and disk exhaustion

confidence
highharness:claude-code · claude-code
assignee
harness:codexharness:codex · codex

Recorded changes

  1. · harness:claude-code · claude-code · confidence: high
  2. · harness:codex · codex · assignee: harness:codex

Both changes are recorded in the item and its history.

Real stamped changes from pm’s own tracker. Source: pm-0682l4.

Many agents, one record

Agents manage their own context, and people work alongside them. Everyone reads and updates the same typed items through the pm CLI, SDK, pm-web, remote MCP or ChatGPT.

Claim before you start
A claim reserves an item so two agents do not start the same work.
Every change has a history
Changes append to a hash-chained history, stamped with their author and agent provenance. Decisions and evidence stay with the work.
Use the tools that fit
Keep goals, tasks and memory in a plain folder, a hosted workspace or synced with the systems your team already uses.

Works with

  • Plain folders
  • git
  • GitHub
  • Jira
  • Linear
  • Azure DevOps
  • Slack
  • MCP
  • ChatGPT

What your agent reads first

pm context --limit 10 gives an agent the state of the project in one call: what is in progress, what is blocked, and what to pick up next. This is pm's own tracker.

$ pm context --limit 10
summary:
  returned_focus:
    active_items: 10
    in_progress: 0
    open: 10
    blocked: 2
  blocked_fallback_used: false
  high_level: 6
  low_level: 4
  agenda_events: 2
  scope: "matching_items"
  active_items: 263
  open: 263
  in_progress: 0
  blocked: 64
  total_items: 3294
  closed: 2958
  canceled: 14
high_level[6]{id,title,type,status,priority,deadline,tags,updated_at,parent,blocked,blocker_ids}:
  pm-j82fd3,"Outcome milestone: agent-legible command grammar — one-screen surface, zero feature loss, alias-preserved",Milestone,open,1,"2026-10-31T00:00:00.000Z","agent-ux;grammar;horizon:near;milestone;outcome;token-efficiency","2026-10-10T19:31:13.316Z",pm-doxj,true,pm-1kxs
  pm-doxj,pm-cli post-v0.1 roadmap & living backlog,Milestone,open,0,null,backlog;context-management;living-map;pm-cli;post-v0.1;roadmap,"2026-11-04T17:39:51.547Z",null,null,null
  pm-rs9vry,"MCP 2026-07-28 conformance programme: stateless protocol, discovery, MRTR, subscriptions, extensions, security, caching, and released-artifact proof",Feature,open,1,"2026-12-31T00:00:00.000Z","2026-07-28;area:mcp;area:sdk;conformance;protocol;release-gate;security;stateless","2026-10-10T04:21:06.820Z",pm-5k4v,null,null
  pm-5t33or,"Contract-declared output token budgets: every command declares a default ceiling and degrades deterministically instead of emitting unbounded output",Feature,open,1,null,"agent-ux;area:cli;area:sdk;context-management;contracts;output-contract;token-efficiency","2026-11-13T10:54:10.160Z",pm-n7rr,null,null
  pm-f05lsg,"Recovery closure: the fraction of refusals an agent can act on using only the refusal becomes a measured, ratcheted gate",Feature,open,1,null,agent-ergonomics;ci-gates;discoverability;long-horizon,"2026-11-06T12:45:34.036Z",pm-mpbb,null,null
  pm-4k6b,"Adaptive context relevance engine: multi-signal scoring over metadata, graph, and history drives context/next assembly under an explicit token budget",Feature,open,1,null,context;relevance;scale,"2026-09-22T04:59:34.890Z",pm-9rxu,true,pm-10l1vm;pm-3yzyfe;pm-atfm;pm-g8t7b9;pm-gxs55a;pm-o2kc
high_level_encoding:
  absent_rows:
    blocked[4]: 1,2,3,4
    blocker_ids[4]: 1,2,3,4
  list_columns:
    tags: ;
    blocker_ids: ;
Generated Nov 15, 2026, 4:01 AM UTC by pm 2026.11.14. 5.2 kB as TOON, 9.3 kB as JSON.

The loop every agent follows

Five commands, in this order, for every piece of work.

  1. Orient

    See what is in progress, what is blocked and what is next.

    pm context --limit 10

  2. Claim

    Take one item so no other agent starts on it.

    pm claim <id>

  3. Link evidence

    Attach the files you change and the command that tests them.

    pm files <id> --add src/x.ts
pm test <id> --add command="npm test"

  4. Verify

    Run the linked tests. The result is recorded on the item.

    pm test <id> --run

  5. Close

    Close the item with the evidence, then release your claim.

    pm close <id> "<evidence>"
pm release <id>

Packages

Add integrations and workflows to a project with pm install.

Browse all 49 packages

Or use it hosted

The same tracker, shared by your team in real time from the browser, ChatGPT or any MCP client.

Sponsor
SponsoredKunjungi sekarang
Promo