boomkin 0.12.0 → 0.12.2
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/CHANGELOG.md +13 -0
- package/README.md +6 -4
- package/catalog/skills.json +20 -20
- package/dist/cli.js +29 -28
- package/docs/CHATGPT.md +1 -1
- package/docs/CONNECTIONS.md +1 -1
- package/docs/DESK.md +1 -1
- package/docs/GETTING-STARTED.md +2 -2
- package/docs/PROVIDERS.md +1 -1
- package/docs/UPDATES.md +2 -2
- package/package.json +2 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,18 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.12.2 · 2026-10-19
|
|
4
|
+
|
|
5
|
+
- Review native Hermes 0.22.2 and pin it for fresh installs. Its installer now provides a managed launcher at `.hermes/bin/hermes` instead of a virtual environment, so Boomkin finds that launcher and still reuses runtimes from earlier layouts.
|
|
6
|
+
- The native compatibility check, isolated installation, onboarding, live doctor and browser model setup pass against 0.22.2.
|
|
7
|
+
|
|
8
|
+
## 0.12.1 · 2026-10-19
|
|
9
|
+
|
|
10
|
+
- Let in-flight local desk requests deliver their responses before the server stops.
|
|
11
|
+
- Review ten independently released skill packs. Hyperliquid 0.4.1 stops counting outcome fills as default perps in wallet audits; LP 0.6.2 covers the 2026-10-22 Aero upgrade that deactivates Aerodrome and Velodrome gauges; derivatives 0.1.6 records Drift's move to Velocity. Agent, governance, infra, lending, routing, security and yield receive dated source updates. Immutable source pins and existing profile selections are preserved.
|
|
12
|
+
- Read native Hermes releases tagged with semantic versions, so the freshness report shows the latest release again instead of "unavailable".
|
|
13
|
+
- State that the compatibility check covers Hermes 0.21.5 and that Hermes 0.22 is not yet reviewed; date the 58 studied skills.eth.sh entries.
|
|
14
|
+
- Say who Boomkin is for, point agent users to the skill packs and describe what the installer checks; credit Galleon Labs in the website footer.
|
|
15
|
+
|
|
3
16
|
## 0.12.0 · 2026-10-12
|
|
4
17
|
|
|
5
18
|
- Add **What changed?** to the local desk: compare a saved research capture against an explicit earlier one for market marks, wallet accounting and strategy results, withholding deltas when inputs, helper revision or source bytes differ.
|
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
**Your open-source DeFi desk.**
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
Boomkin is for people who research DeFi and want to keep the evidence. It is a local browser desk, a catalog of reviewed research workflows and an installer that pins and checks the Galleon skill packs. Research an asset, review public wallet costs or test a strategy; the result, its sources and the run history stay on your computer. Add native [Hermes research](https://github.com/NousResearch/hermes-agent) when you want to investigate further.
|
|
6
6
|
|
|
7
7
|
[](https://galleonlabs.github.io/boomkin/docs/desk/)
|
|
8
8
|
|
|
@@ -10,6 +10,8 @@ Research an asset, review public wallet costs and test a strategy in a simple lo
|
|
|
10
10
|
|
|
11
11
|
The browser demo needs no installation. Choose a research rule, compare held-out periods and higher trading costs, and inspect simulated trades using a dated Bitcoin capture, synthetic prices or your own dataset. Uploaded data stays in your browser.
|
|
12
12
|
|
|
13
|
+
Only want the skills inside Claude Code, Codex, Cursor or another agent you already use? Install them from [crypto-defi-skills](https://github.com/galleonlabs/crypto-defi-skills).
|
|
14
|
+
|
|
13
15
|
**31 workflows · 60 providers in discovery · 17 independent packs · 49 reviewed skills**
|
|
14
16
|
|
|
15
17
|
[](https://github.com/galleonlabs/boomkin/actions/workflows/ci.yml)
|
|
@@ -21,7 +23,7 @@ The browser demo needs no installation. Choose a research rule, compare held-out
|
|
|
21
23
|
Use macOS or Linux with [Bun](https://bun.sh) 1.3.12+ and Git. Windows users can use WSL2.
|
|
22
24
|
|
|
23
25
|
```bash
|
|
24
|
-
bun install -g boomkin@0.12.
|
|
26
|
+
bun install -g boomkin@0.12.2
|
|
25
27
|
boomkin desk
|
|
26
28
|
```
|
|
27
29
|
|
|
@@ -105,7 +107,7 @@ boomkin providers --capability Data --access keyless
|
|
|
105
107
|
boomkin providers --provider blockscout
|
|
106
108
|
```
|
|
107
109
|
|
|
108
|
-
The directory covers 58
|
|
110
|
+
The directory covers the 58 [skills.eth.sh](https://skills.eth.sh/) entries studied on October 8, 2026 and two existing connections. Dated sources distinguish authorship, access, cost and authority. Discovery does not install or connect all 60 providers. Keyless access can still cost money; wallet and x402 capabilities need separate choices. [Provider guide](docs/PROVIDERS.md)
|
|
109
111
|
|
|
110
112
|
## Connect your tools
|
|
111
113
|
|
|
@@ -129,7 +131,7 @@ Fresh onboarding includes all 17 packs. Repeated `--pack` options choose fewer;
|
|
|
129
131
|
## Updates and recovery
|
|
130
132
|
|
|
131
133
|
```bash
|
|
132
|
-
bun install -g boomkin@0.12.
|
|
134
|
+
bun install -g boomkin@0.12.2
|
|
133
135
|
boomkin check --directory "$HOME/.boomkin/hermes"
|
|
134
136
|
boomkin update --directory "$HOME/.boomkin/hermes"
|
|
135
137
|
boomkin doctor --directory "$HOME/.boomkin/hermes" --live
|
package/catalog/skills.json
CHANGED
|
@@ -5,8 +5,8 @@
|
|
|
5
5
|
"id": "lp-skills",
|
|
6
6
|
"source": "galleonlabs/crypto-defi-skills",
|
|
7
7
|
"description": "Agent skills and deterministic tools for Uniswap and Aerodrome liquidity provision.",
|
|
8
|
-
"version": "0.6.
|
|
9
|
-
"revision": "
|
|
8
|
+
"version": "0.6.2",
|
|
9
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
10
10
|
"skills": [
|
|
11
11
|
"aerodrome-slipstream",
|
|
12
12
|
"lp-analyze",
|
|
@@ -24,8 +24,8 @@
|
|
|
24
24
|
"id": "hyperliquid-skills",
|
|
25
25
|
"source": "galleonlabs/crypto-defi-skills",
|
|
26
26
|
"description": "Hyperliquid market research, trade planning, monitoring, performance review and reproducible public wallet cost audits.",
|
|
27
|
-
"version": "0.4.
|
|
28
|
-
"revision": "
|
|
27
|
+
"version": "0.4.1",
|
|
28
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
29
29
|
"skills": [
|
|
30
30
|
"hyperliquid-analyze",
|
|
31
31
|
"hyperliquid-engineer",
|
|
@@ -43,8 +43,8 @@
|
|
|
43
43
|
"id": "defi-infra-skills",
|
|
44
44
|
"source": "galleonlabs/crypto-defi-skills",
|
|
45
45
|
"description": "RPC, wallet and Hermes infrastructure skills with read-only readiness diagnostics.",
|
|
46
|
-
"version": "0.4.
|
|
47
|
-
"revision": "
|
|
46
|
+
"version": "0.4.2",
|
|
47
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
48
48
|
"skills": [
|
|
49
49
|
"galleon-coinbase-agentkit-readiness",
|
|
50
50
|
"galleon-defi-infra"
|
|
@@ -71,8 +71,8 @@
|
|
|
71
71
|
"id": "defi-lending-skills",
|
|
72
72
|
"source": "galleonlabs/crypto-defi-skills",
|
|
73
73
|
"description": "Research lending markets, plan borrowing and monitor liquidation exposure.",
|
|
74
|
-
"version": "0.3.
|
|
75
|
-
"revision": "
|
|
74
|
+
"version": "0.3.2",
|
|
75
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
76
76
|
"skills": [
|
|
77
77
|
"galleon-aave-position",
|
|
78
78
|
"galleon-aave-v4",
|
|
@@ -100,8 +100,8 @@
|
|
|
100
100
|
"id": "defi-yield-skills",
|
|
101
101
|
"source": "galleonlabs/crypto-defi-skills",
|
|
102
102
|
"description": "Evaluate vaults and yield tokens, including liquidity and maturity.",
|
|
103
|
-
"version": "0.3.
|
|
104
|
-
"revision": "
|
|
103
|
+
"version": "0.3.1",
|
|
104
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
105
105
|
"skills": [
|
|
106
106
|
"galleon-defi-yield",
|
|
107
107
|
"galleon-pendle-maturity",
|
|
@@ -126,8 +126,8 @@
|
|
|
126
126
|
"id": "defi-routing-skills",
|
|
127
127
|
"source": "galleonlabs/crypto-defi-skills",
|
|
128
128
|
"description": "Compare swaps and bridges and track cross-chain settlement.",
|
|
129
|
-
"version": "0.3.
|
|
130
|
-
"revision": "
|
|
129
|
+
"version": "0.3.2",
|
|
130
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
131
131
|
"skills": [
|
|
132
132
|
"galleon-defi-routing",
|
|
133
133
|
"lifi-cross-chain",
|
|
@@ -140,8 +140,8 @@
|
|
|
140
140
|
"id": "defi-derivatives-skills",
|
|
141
141
|
"source": "galleonlabs/crypto-defi-skills",
|
|
142
142
|
"description": "Plan derivatives positions and reconcile venue execution.",
|
|
143
|
-
"version": "0.1.
|
|
144
|
-
"revision": "
|
|
143
|
+
"version": "0.1.6",
|
|
144
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
145
145
|
"skills": [
|
|
146
146
|
"galleon-defi-derivatives"
|
|
147
147
|
],
|
|
@@ -164,8 +164,8 @@
|
|
|
164
164
|
"id": "defi-security-skills",
|
|
165
165
|
"source": "galleonlabs/crypto-defi-skills",
|
|
166
166
|
"description": "Investigate token risks, compare evidence and review transaction permissions.",
|
|
167
|
-
"version": "0.2.
|
|
168
|
-
"revision": "
|
|
167
|
+
"version": "0.2.4",
|
|
168
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
169
169
|
"skills": [
|
|
170
170
|
"galleon-defi-security",
|
|
171
171
|
"galleon-defi-security-token-diligence"
|
|
@@ -191,8 +191,8 @@
|
|
|
191
191
|
"id": "defi-governance-skills",
|
|
192
192
|
"source": "galleonlabs/crypto-defi-skills",
|
|
193
193
|
"description": "Research proposals, prepare votes and track governance execution.",
|
|
194
|
-
"version": "0.1.
|
|
195
|
-
"revision": "
|
|
194
|
+
"version": "0.1.4",
|
|
195
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
196
196
|
"skills": [
|
|
197
197
|
"galleon-defi-governance"
|
|
198
198
|
],
|
|
@@ -215,8 +215,8 @@
|
|
|
215
215
|
"id": "defi-agent-skills",
|
|
216
216
|
"source": "galleonlabs/crypto-defi-skills",
|
|
217
217
|
"description": "Construct unsigned DeFi plans and verify exact transaction simulation evidence.",
|
|
218
|
-
"version": "0.1.
|
|
219
|
-
"revision": "
|
|
218
|
+
"version": "0.1.2",
|
|
219
|
+
"revision": "86130b45757a53dad00fd8a4701750baf3528674",
|
|
220
220
|
"skills": [
|
|
221
221
|
"galleon-defi-agent-plan",
|
|
222
222
|
"galleon-defi-agent-simulate"
|
package/dist/cli.js
CHANGED
|
@@ -7599,8 +7599,8 @@ var skills_default = {
|
|
|
7599
7599
|
id: "lp-skills",
|
|
7600
7600
|
source: "galleonlabs/crypto-defi-skills",
|
|
7601
7601
|
description: "Agent skills and deterministic tools for Uniswap and Aerodrome liquidity provision.",
|
|
7602
|
-
version: "0.6.
|
|
7603
|
-
revision: "
|
|
7602
|
+
version: "0.6.2",
|
|
7603
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7604
7604
|
skills: [
|
|
7605
7605
|
"aerodrome-slipstream",
|
|
7606
7606
|
"lp-analyze",
|
|
@@ -7618,8 +7618,8 @@ var skills_default = {
|
|
|
7618
7618
|
id: "hyperliquid-skills",
|
|
7619
7619
|
source: "galleonlabs/crypto-defi-skills",
|
|
7620
7620
|
description: "Hyperliquid market research, trade planning, monitoring, performance review and reproducible public wallet cost audits.",
|
|
7621
|
-
version: "0.4.
|
|
7622
|
-
revision: "
|
|
7621
|
+
version: "0.4.1",
|
|
7622
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7623
7623
|
skills: [
|
|
7624
7624
|
"hyperliquid-analyze",
|
|
7625
7625
|
"hyperliquid-engineer",
|
|
@@ -7637,8 +7637,8 @@ var skills_default = {
|
|
|
7637
7637
|
id: "defi-infra-skills",
|
|
7638
7638
|
source: "galleonlabs/crypto-defi-skills",
|
|
7639
7639
|
description: "RPC, wallet and Hermes infrastructure skills with read-only readiness diagnostics.",
|
|
7640
|
-
version: "0.4.
|
|
7641
|
-
revision: "
|
|
7640
|
+
version: "0.4.2",
|
|
7641
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7642
7642
|
skills: [
|
|
7643
7643
|
"galleon-coinbase-agentkit-readiness",
|
|
7644
7644
|
"galleon-defi-infra"
|
|
@@ -7665,8 +7665,8 @@ var skills_default = {
|
|
|
7665
7665
|
id: "defi-lending-skills",
|
|
7666
7666
|
source: "galleonlabs/crypto-defi-skills",
|
|
7667
7667
|
description: "Research lending markets, plan borrowing and monitor liquidation exposure.",
|
|
7668
|
-
version: "0.3.
|
|
7669
|
-
revision: "
|
|
7668
|
+
version: "0.3.2",
|
|
7669
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7670
7670
|
skills: [
|
|
7671
7671
|
"galleon-aave-position",
|
|
7672
7672
|
"galleon-aave-v4",
|
|
@@ -7694,8 +7694,8 @@ var skills_default = {
|
|
|
7694
7694
|
id: "defi-yield-skills",
|
|
7695
7695
|
source: "galleonlabs/crypto-defi-skills",
|
|
7696
7696
|
description: "Evaluate vaults and yield tokens, including liquidity and maturity.",
|
|
7697
|
-
version: "0.3.
|
|
7698
|
-
revision: "
|
|
7697
|
+
version: "0.3.1",
|
|
7698
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7699
7699
|
skills: [
|
|
7700
7700
|
"galleon-defi-yield",
|
|
7701
7701
|
"galleon-pendle-maturity",
|
|
@@ -7720,8 +7720,8 @@ var skills_default = {
|
|
|
7720
7720
|
id: "defi-routing-skills",
|
|
7721
7721
|
source: "galleonlabs/crypto-defi-skills",
|
|
7722
7722
|
description: "Compare swaps and bridges and track cross-chain settlement.",
|
|
7723
|
-
version: "0.3.
|
|
7724
|
-
revision: "
|
|
7723
|
+
version: "0.3.2",
|
|
7724
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7725
7725
|
skills: [
|
|
7726
7726
|
"galleon-defi-routing",
|
|
7727
7727
|
"lifi-cross-chain",
|
|
@@ -7734,8 +7734,8 @@ var skills_default = {
|
|
|
7734
7734
|
id: "defi-derivatives-skills",
|
|
7735
7735
|
source: "galleonlabs/crypto-defi-skills",
|
|
7736
7736
|
description: "Plan derivatives positions and reconcile venue execution.",
|
|
7737
|
-
version: "0.1.
|
|
7738
|
-
revision: "
|
|
7737
|
+
version: "0.1.6",
|
|
7738
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7739
7739
|
skills: [
|
|
7740
7740
|
"galleon-defi-derivatives"
|
|
7741
7741
|
],
|
|
@@ -7758,8 +7758,8 @@ var skills_default = {
|
|
|
7758
7758
|
id: "defi-security-skills",
|
|
7759
7759
|
source: "galleonlabs/crypto-defi-skills",
|
|
7760
7760
|
description: "Investigate token risks, compare evidence and review transaction permissions.",
|
|
7761
|
-
version: "0.2.
|
|
7762
|
-
revision: "
|
|
7761
|
+
version: "0.2.4",
|
|
7762
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7763
7763
|
skills: [
|
|
7764
7764
|
"galleon-defi-security",
|
|
7765
7765
|
"galleon-defi-security-token-diligence"
|
|
@@ -7785,8 +7785,8 @@ var skills_default = {
|
|
|
7785
7785
|
id: "defi-governance-skills",
|
|
7786
7786
|
source: "galleonlabs/crypto-defi-skills",
|
|
7787
7787
|
description: "Research proposals, prepare votes and track governance execution.",
|
|
7788
|
-
version: "0.1.
|
|
7789
|
-
revision: "
|
|
7788
|
+
version: "0.1.4",
|
|
7789
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7790
7790
|
skills: [
|
|
7791
7791
|
"galleon-defi-governance"
|
|
7792
7792
|
],
|
|
@@ -7809,8 +7809,8 @@ var skills_default = {
|
|
|
7809
7809
|
id: "defi-agent-skills",
|
|
7810
7810
|
source: "galleonlabs/crypto-defi-skills",
|
|
7811
7811
|
description: "Construct unsigned DeFi plans and verify exact transaction simulation evidence.",
|
|
7812
|
-
version: "0.1.
|
|
7813
|
-
revision: "
|
|
7812
|
+
version: "0.1.2",
|
|
7813
|
+
revision: "86130b45757a53dad00fd8a4701750baf3528674",
|
|
7814
7814
|
skills: [
|
|
7815
7815
|
"galleon-defi-agent-plan",
|
|
7816
7816
|
"galleon-defi-agent-simulate"
|
|
@@ -7836,7 +7836,7 @@ var skills_default = {
|
|
|
7836
7836
|
// package.json
|
|
7837
7837
|
var package_default = {
|
|
7838
7838
|
name: "boomkin",
|
|
7839
|
-
version: "0.12.
|
|
7839
|
+
version: "0.12.2",
|
|
7840
7840
|
description: "Your open-source DeFi desk: native Hermes research projects, verifiable evidence and independent financial skills.",
|
|
7841
7841
|
type: "module",
|
|
7842
7842
|
license: "MIT",
|
|
@@ -7895,6 +7895,7 @@ var package_default = {
|
|
|
7895
7895
|
"ai-agent",
|
|
7896
7896
|
"agent-skills",
|
|
7897
7897
|
"hermes",
|
|
7898
|
+
"hermes-agent",
|
|
7898
7899
|
"mcp",
|
|
7899
7900
|
"research",
|
|
7900
7901
|
"backtesting",
|
|
@@ -8001,9 +8002,9 @@ async function terminateOwnedProcess(child, group, graceMs = 2000) {
|
|
|
8001
8002
|
}
|
|
8002
8003
|
|
|
8003
8004
|
// src/hermes.ts
|
|
8004
|
-
var HERMES_VERSION = "0.
|
|
8005
|
-
var HERMES_COMMIT = "
|
|
8006
|
-
var HERMES_INSTALLER_SHA256 = "
|
|
8005
|
+
var HERMES_VERSION = "0.22.2";
|
|
8006
|
+
var HERMES_COMMIT = "d923a5eb487a17c0a68801bba9ef0f56c81040a8";
|
|
8007
|
+
var HERMES_INSTALLER_SHA256 = "f4cdb0e20f1aca2c3871a76b962fd4db61510f549cf973759c753ac13349beb5";
|
|
8007
8008
|
var HERMES_INSTALLER_URL = `https://raw.githubusercontent.com/NousResearch/hermes-agent/${HERMES_COMMIT}/scripts/install.sh`;
|
|
8008
8009
|
function absent(error) {
|
|
8009
8010
|
return error.code === "ENOENT";
|
|
@@ -8077,7 +8078,7 @@ async function findRuntime(directory) {
|
|
|
8077
8078
|
const root = await profilePath(directory);
|
|
8078
8079
|
const runtime = join(root, ".boomkin", "runtime");
|
|
8079
8080
|
await safePath(runtime);
|
|
8080
|
-
for (const path of [join(runtime, ".venv", "bin", "hermes"), join(runtime, "venv", "bin", "hermes")]) {
|
|
8081
|
+
for (const path of [join(runtime, ".hermes", "bin", "hermes"), join(runtime, ".venv", "bin", "hermes"), join(runtime, "venv", "bin", "hermes")]) {
|
|
8081
8082
|
if (await executableAt(path))
|
|
8082
8083
|
return path;
|
|
8083
8084
|
}
|
|
@@ -8136,7 +8137,7 @@ async function ensureRuntime(directory, options) {
|
|
|
8136
8137
|
throw new Error("Hermes runtime is missing. Run onboarding with runtime installation enabled.");
|
|
8137
8138
|
const runtime = join(root, ".boomkin", "runtime");
|
|
8138
8139
|
if (options.dryRun) {
|
|
8139
|
-
const planned = join(runtime, "
|
|
8140
|
+
const planned = join(runtime, ".hermes", "bin", "hermes");
|
|
8140
8141
|
console.log(`Would install Hermes ${HERMES_VERSION} at ${planned}`);
|
|
8141
8142
|
return planned;
|
|
8142
8143
|
}
|
|
@@ -12668,7 +12669,7 @@ ${evidence.map((item) => `[${item.id}] ${item.summary}`).join(`
|
|
|
12668
12669
|
const contents = await readFile5(filePath);
|
|
12669
12670
|
return new Response(request.method === "HEAD" ? null : contents, { headers: { ...headers, "content-type": file.type } });
|
|
12670
12671
|
} catch (error) {
|
|
12671
|
-
const status2 = error instanceof DeskError ? error.status : error
|
|
12672
|
+
const status2 = error instanceof DeskError ? error.status : error?.code === "ENOENT" ? 404 : 500;
|
|
12672
12673
|
return response({ error: { message: status2 === 500 ? "Desk operation failed; saved files were preserved" : error.message } }, status2);
|
|
12673
12674
|
}
|
|
12674
12675
|
}
|
|
@@ -12695,7 +12696,7 @@ ${evidence.map((item) => `[${item.id}] ${item.summary}`).join(`
|
|
|
12695
12696
|
entry.controller.abort();
|
|
12696
12697
|
await Promise.allSettled([...active.values()].map((entry) => entry.done));
|
|
12697
12698
|
await Promise.allSettled([profilePromise, setupPromise]);
|
|
12698
|
-
server.stop(
|
|
12699
|
+
await server.stop();
|
|
12699
12700
|
await rm3(lock, { recursive: true, force: true });
|
|
12700
12701
|
})();
|
|
12701
12702
|
return stopping;
|
package/docs/CHATGPT.md
CHANGED
|
@@ -6,7 +6,7 @@ Examples use the installed `boomkin` command; from source, use `bun run boomkin`
|
|
|
6
6
|
|
|
7
7
|
[OpenAI lists Hermes Agent as a ChatGPT plan-usage partner](https://learn.chatgpt.com/docs/sign-in-with-chatgpt). Account sign-in, permission to consume plan usage, a successful inference and usage attributed to Hermes are separate milestones. Boomkin is an onboarding layer, not a separately registered OpenAI partner.
|
|
8
8
|
|
|
9
|
-
Boomkin retains reviewed Hermes 0.
|
|
9
|
+
Boomkin retains reviewed Hermes 0.22.2 at `d923a5eb487a17c0a68801bba9ef0f56c81040a8`. Its native `auth add openai-codex --type oauth` supports a fresh ChatGPT device login, profile-native credential pools and refresh; `auth status` reports authentication. Its source uses the Codex OAuth client and Codex inference route. This proves native ChatGPT OAuth capability; it does **not** prove the new Hermes partner plan-consent or per-app attribution path. Use the [official Nous portal](https://portal.nousresearch.com/) for the partner connection and review its actual permission screen. Do not replace the pinned runtime or invent partner client IDs/endpoints to bridge that gap.
|
|
10
10
|
|
|
11
11
|
```sh
|
|
12
12
|
boomkin chatgpt --action login --directory /absolute/path/to/boomkin-profile
|
package/docs/CONNECTIONS.md
CHANGED
|
@@ -10,7 +10,7 @@ Provider-specific review dates and limits appear below. The broader discovery ca
|
|
|
10
10
|
|
|
11
11
|
`boomkin onboard` runs the official pinned Hermes installer when needed and opens `hermes setup model` with the selected `HERMES_HOME`. Use `boomkin model` to revisit setup, and `boomkin start` for native chat. From a source checkout, use `bun run boomkin`. Model keys, OAuth and local models use Hermes's facilities. A configured model name or CLI version is not proof of authentication.
|
|
12
12
|
|
|
13
|
-
Hermes v0.
|
|
13
|
+
Hermes v0.22.2 (upstream tag `v0.22.2`) at [the reviewed source](https://github.com/NousResearch/hermes-agent/tree/d923a5eb487a17c0a68801bba9ef0f56c81040a8) was tested. Boomkin pins the official installer and runtime for a fresh install. Existing installations are preserved. Native setup supports optional browser, tools and messaging features; configure those through Hermes rather than a second runtime.
|
|
14
14
|
|
|
15
15
|
The selected directory holds `config.yaml`, `.env`, `SOUL.md`, `skills/` and native state. Boomkin stores its own records under `.boomkin/`. Commands explicitly select the root profile so a sticky Hermes profile preference cannot redirect them elsewhere. Do not move a configured profile without reviewing saved paths and credentials.
|
|
16
16
|
|
package/docs/DESK.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
Open Boomkin in your browser, choose a question and keep the result with its sources. Market snapshots, public Hyperliquid wallet reviews and daily strategy tests work without a model account or funded wallet.
|
|
4
4
|
|
|
5
5
|
```bash
|
|
6
|
-
bun install -g boomkin@0.12.
|
|
6
|
+
bun install -g boomkin@0.12.2
|
|
7
7
|
boomkin desk
|
|
8
8
|
```
|
|
9
9
|
|
package/docs/GETTING-STARTED.md
CHANGED
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
Use macOS or Linux with [Bun](https://bun.sh) 1.3.12+ and Git. Keep Bun's global bin directory on your shell path. Windows users can use WSL2; an existing native Windows Hermes installation can also be reused through its official flow.
|
|
10
10
|
|
|
11
11
|
```bash
|
|
12
|
-
bun install -g boomkin@0.12.
|
|
12
|
+
bun install -g boomkin@0.12.2
|
|
13
13
|
boomkin desk
|
|
14
14
|
```
|
|
15
15
|
|
|
@@ -69,7 +69,7 @@ boomkin model --directory "$HOME/research-desk"
|
|
|
69
69
|
|
|
70
70
|
Hermes owns chat, tools, memory, sessions, scheduling and model authentication. Boomkin supplies reviewed financial procedures, source pins, installation checks and research projects. Other harness adapters install [skills only](HARNESSES.md).
|
|
71
71
|
|
|
72
|
-
A fresh runtime installation uses reviewed Hermes 0.
|
|
72
|
+
A fresh runtime installation uses reviewed Hermes 0.22.2, upstream tag `v0.22.2`, through its pinned official installer, which manages its own Python 3.14 runtime. A working existing Hermes installation at 0.21.0 or newer is reused; the compatibility check covers 0.22.2. Browser/computer-use dependencies are skipped initially; configure optional features through native Hermes setup. The reviewed runtime source and installer checksum live in [src/hermes.ts](../src/hermes.ts).
|
|
73
73
|
|
|
74
74
|
CoinGecko is the sole onboarding data connection. Optional provider setup stays explicit; [provider discovery](PROVIDERS.md) separates source references from the smaller native connection list. Tool availability, account authority and financial execution are different outcomes.
|
|
75
75
|
|
package/docs/PROVIDERS.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Find a provider by capability and authority
|
|
2
2
|
|
|
3
|
-
Boomkin's local discovery catalog studies
|
|
3
|
+
Boomkin's local discovery catalog studies the 58 entries that [skills.eth.sh](https://skills.eth.sh/) listed on October 8, 2026, plus the existing AIXBT and Coinbase account connections. Entries added since then are not yet reviewed. Primary documentation, repository instructions and public package readmes were reviewed on October 8, 2026. Discovery records a tool's capabilities, authorship, prerequisites, cost and financial authority separately. It makes no network call, installs no third-party skill and grants no account permissions.
|
|
4
4
|
|
|
5
5
|
```bash
|
|
6
6
|
boomkin providers
|
package/docs/UPDATES.md
CHANGED
|
@@ -9,7 +9,7 @@ Maintain Boomkin, its selected skill packs and the Hermes runtime separately. Us
|
|
|
9
9
|
For the installed CLI and default profile:
|
|
10
10
|
|
|
11
11
|
```bash
|
|
12
|
-
bun install -g boomkin@0.12.
|
|
12
|
+
bun install -g boomkin@0.12.2
|
|
13
13
|
boomkin check --directory "$HOME/.boomkin/hermes"
|
|
14
14
|
boomkin update --directory "$HOME/.boomkin/hermes"
|
|
15
15
|
boomkin doctor --directory "$HOME/.boomkin/hermes" --live
|
|
@@ -22,7 +22,7 @@ Replace the directory in every command if you use another profile. Restart an ac
|
|
|
22
22
|
| --- | --- |
|
|
23
23
|
| Boomkin CLI and packaged guides | Install the desired published Boomkin version with Bun |
|
|
24
24
|
| Selected skill packs | Run `boomkin update` in the chosen profile |
|
|
25
|
-
| Hermes runtime | Use native Hermes updates, then rerun `doctor --live
|
|
25
|
+
| Hermes runtime | Use native Hermes updates, then rerun `doctor --live`. Boomkin has reviewed 0.22.2; from 0.22, source installs follow stable releases by default |
|
|
26
26
|
| Provider credentials and tools | Follow the provider's native [connection setup](CONNECTIONS.md) |
|
|
27
27
|
|
|
28
28
|
From a source checkout, first pull the reviewed branch and its locked dependencies, then use `bun run boomkin` in place of `boomkin`:
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "boomkin",
|
|
3
|
-
"version": "0.12.
|
|
3
|
+
"version": "0.12.2",
|
|
4
4
|
"description": "Your open-source DeFi desk: native Hermes research projects, verifiable evidence and independent financial skills.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -59,6 +59,7 @@
|
|
|
59
59
|
"ai-agent",
|
|
60
60
|
"agent-skills",
|
|
61
61
|
"hermes",
|
|
62
|
+
"hermes-agent",
|
|
62
63
|
"mcp",
|
|
63
64
|
"research",
|
|
64
65
|
"backtesting",
|