hivemind-agents 0.1.2 → 0.1.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +15 -1
- package/dist/hivemind.mjs +72 -65
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -28,6 +28,13 @@ Check whether your current work depends on the breaking changes above and adapt
|
|
|
28
28
|
At session start it gets the whole plan: goals, contracts (API shapes, schemas, shared types),
|
|
29
29
|
decisions, who's doing what, and open questions.
|
|
30
30
|
|
|
31
|
+
## Starting a plan
|
|
32
|
+
|
|
33
|
+
Just ask your agent, e.g. *"We're 3 people building X this weekend. Make a plan for the team."* It
|
|
34
|
+
records goals, contracts, decisions and tasks in hivemind (tasks unassigned, with dependencies), and
|
|
35
|
+
each teammate's agent can claim one by key. You can also add things yourself with `hivemind add` or
|
|
36
|
+
in the dashboard (`hivemind open`).
|
|
37
|
+
|
|
31
38
|
## How it works
|
|
32
39
|
|
|
33
40
|
```
|
|
@@ -46,7 +53,7 @@ decisions, who's doing what, and open questions.
|
|
|
46
53
|
- **The plan updates itself.** When an agent finishes a turn, a background extractor reads only the
|
|
47
54
|
new part of its transcript and pulls out the things teammates need: contracts, decisions and task
|
|
48
55
|
progress, each with a quote as evidence. Agents can also publish explicitly through MCP tools
|
|
49
|
-
(`contract_publish`, `decision_log`, `task_claim`, …), and they're told to for anything urgent.
|
|
56
|
+
(`contract_publish`, `decision_log`, `task_add`, `task_claim`, …), and they're told to for anything urgent.
|
|
50
57
|
- **Updates arrive in seconds.** Typically 2–5 s from one agent's change to the other machine,
|
|
51
58
|
then shown at that agent's next tool call.
|
|
52
59
|
|
|
@@ -79,6 +86,7 @@ hivemind plan print the shared plan
|
|
|
79
86
|
hivemind open live dashboard in your browser (and a form to add to the plan)
|
|
80
87
|
hivemind add <goal|task|contract|decision|question> <key> <text> [--breaking]
|
|
81
88
|
hivemind doctor check that everything is wired up
|
|
89
|
+
hivemind disable turn hivemind off for this clone (hivemind enable to undo)
|
|
82
90
|
hivemind uninstall remove hooks and MCP config (your repos' plan data is left alone)
|
|
83
91
|
```
|
|
84
92
|
|
|
@@ -86,6 +94,12 @@ hivemind uninstall remove hooks and MCP config (your repos' plan data is left
|
|
|
86
94
|
|
|
87
95
|
- **Your plan data never leaves your git host.** There's no hivemind server. Anyone with read
|
|
88
96
|
access to the repo can read its plan refs, the same people who can read the code.
|
|
97
|
+
- **Public repo = public plan.** hivemind detects public GitHub repos and tells your agent (and
|
|
98
|
+
`hivemind status`) so nobody is surprised. Don't want that? `hivemind disable` turns it off for
|
|
99
|
+
that clone; `hivemind enable` turns it back on.
|
|
100
|
+
- **Secrets are scrubbed.** Every plan entry is checked for keys, tokens, passwords and connection-string
|
|
101
|
+
credentials before it's written, and the extractor is instructed to leave out credentials, personal
|
|
102
|
+
details, customer names and unfixed security issues.
|
|
89
103
|
- **Extraction runs on your machine with your own agent login.** It calls `claude -p` with Haiku
|
|
90
104
|
(or `codex exec` if you only have Codex) using your existing subscription or API key: about
|
|
91
105
|
$0.005 per extraction on API pricing, or a small slice of your subscription usage. Set
|