Not in the top 1,000 by GitHub stars

dreamers-laboratory/agent-fleet-manager

A general-purpose engine for large-scale, repeated information gathering by a fleet of workers.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

31261ed70ae3 → 31261ed70ae3

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 31261ed70ae3

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 31261ed70ae3044b9fb9d03b1de8c707996e61c5

107GitHub stars

-32stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.0

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

agent-fleet-manager /

How it works

agent-fleet-manager

When your agent uses it

Operate an agentfleet fleet for large-scale periodic information gathering. Use when the user wants to monitor many sources on a schedule (prospect signals, competitor pages, regulatory updates, listings, datasets), act as a worker executing leased batches, review what changed or failed across the fleet, or export fleet activity as OpenTelemetry traces.

What it loads into context

Frontmatter

75 tokens

Always available to the agent

SKILL.md

861 tokens

When the skill is activated

Reference documents

2,059 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Register what to watch
Run a sweep
Act as a worker yourself
Optional Jev evaluation
Review the fleet
Export telemetry

Scripts executed separately

agentfleet/__init__.py
agentfleet/cli.py
agentfleet/engine.py
agentfleet/jev.py
agentfleet/otel.py
examples/demo.py
tests/test_engine.py
tests/test_jev.py

Files

.gitignoreasset62 bytes
CHANGELOG.mddoc834 bytes
LICENSEasset11,358 bytes
README.mddoc8,268 bytes
SKILL.mdcore3,719 bytes
SKILL.mdcore3,719 bytes
SKILL.mdcore3,719 bytes
agentfleet/__init__.pyruns155 bytes
agentfleet/cli.pyruns5,975 bytes
agentfleet/engine.pyruns10,061 bytes
agentfleet/jev.pyruns8,801 bytes
agentfleet/otel.pyruns3,838 bytes
agentfleet/schema.sqlasset2,541 bytes
examples/demo.pyruns2,042 bytes
examples/jev_questions.jsonasset420 bytes
examples/jev_request.jsonasset525 bytes
tests/test_engine.pyruns4,077 bytes
tests/test_jev.pyruns12,697 bytes

Read SKILL.md


# Operating an agentfleet fleet

One SQLite file holds the whole fleet. All commands take `--db <path>`. Full mechanics are in [README.md](README.md); this file is the operating procedure.

## Register what to watch

```
python -m agentfleet.cli add-source --db fleet.db <name> <route> --cadence <seconds>
```

The route means whatever your worker decides: a URL for the built-in HTTP fetcher, a search query, an API endpoint, a natural-language instruction for an agent worker. Pick cadences honestly — a careers page is an hourly-to-daily source; a statute database is weekly. Do not register sources the user has no right to fetch, and respect robots.txt and rate expectations when the worker is a fetcher you control.

## Run a sweep

View the complete source on GitHub

Skills included

agent-fleet-manager

Repository facts

License: Apache-2.0
Created: Sep 2, 2026
Last pushed: Oct 1, 2026
Forks: 0
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 2 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
31 network referencesin 7 files: README.md:10 agentfleet/cli.py:3 agentfleet/otel.py:85 and 4 more
No hidden or obfuscated text
No instruction overrides
8 executable scriptsin 8 files: agentfleet/__init__.py:1 agentfleet/cli.py:1 agentfleet/engine.py:1 and 5 more
13 references to secretsin 5 files: tests/test_jev.py:52 agentfleet/jev.py:106 README.md:46 and 2 more
No requests to vote in Hot

Show all 52 signals by file

`.gitignore`

Access to secretsline 7
```
[Credential-related source omitted]
```

`LICENSE`

Network accessline 2

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

Network accessline 4
```
http://www.apache.org/licenses/
```

Network accessline 196

http://www.apache.org/licenses/LICENSE-2.0

`README.md`

Network accessline 10

- **Competitor and price watch.** Pricing pages, feature pages, changelogs, app-store listings — checked on cadence, with `changed` flags you can alert on and history you can chart. - **Regulatory and compliance tracking.** Agency pages, st

Network accessline 11

- **Regulatory and compliance tracking.** Agency pages, statute databases, published guidance. The hash ledger doubles as evidence of when a change appeared and when you saw it. - **Research corpus upkeep.** Datasets, preprint feeds, docume

Network accessline 12

- **Research corpus upkeep.** Datasets, preprint feeds, documentation sets that must stay current. Re-ingest is safe because everything is idempotent by hash. Research-tool example: [alphaXiv](https://x.com/askalphaxiv/status/20947979329941

Network accessline 34

python -m agentfleet.cli add-source --db fleet.db acme-careers https://example.com/careers --cadence 3600

Network accessline 44

Use [TypeSafe's direct API](https://docs.typesafe.ai/api) to classify fetched text or explicit structured state. No SDK, gateway, database migration or key is needed for normal fleet operation. Jev is disabled unless requested.

Access to secretsline 46
```
[Credential-related source omitted]
```
Access to secretsline 73
```
[Credential-related source omitted]
```

Network accessline 96

python -m agentfleet.cli export-otel --db fleet.db --endpoint http://localhost:4318

Network accessline 101

Apache-2.0. Built by [Dreamers Inc](https://thedreamers.us).

`SKILL.md`

Access to secretsline 40
```
[Credential-related source omitted]
```

`agentfleet/init.py`

Executable scriptline 1
```
Executable file
```

`agentfleet/cli.py`

Executable scriptline 1
```
Executable file
```

Network accessline 3

python -m agentfleet.cli init --db fleet.db     python -m agentfleet.cli add-source --db fleet.db docs https://example.com/docs --cadence 3600

Network accessline 4

python -m agentfleet.cli add-source --db fleet.db docs https://example.com/docs --cadence 3600

Network accessline 5

python -m agentfleet.cli sweep --db fleet.db --scopes ./scopes     python -m agentfleet.cli status --db fleet.db     python -m agentfleet.cli export-otel --db fleet.db [--endpoint http://localhost:4318]

Network accessline 6

python -m agentfleet.cli status --db fleet.db     python -m agentfleet.cli export-otel --db fleet.db [--endpoint http://localhost:4318] """

Network accessline 7

python -m agentfleet.cli export-otel --db fleet.db [--endpoint http://localhost:4318]

Network accessline 17

def http_executor(route: str):     with urllib.request.urlopen(route, timeout=30) as resp:

Network accessline 18

with urllib.request.urlopen(route, timeout=30) as resp:

`agentfleet/engine.py`

Executable scriptline 1
```
Executable file
```

`agentfleet/jev.py`

Executable scriptline 1
```
Executable file
```

Network accessline 9

ENDPOINT = "https://api.typesafe.ai/v1/systemone"

Access to secretsline 106
```
[Credential-related source omitted]
```
Access to secretsline 112
```
[Credential-related source omitted]
```
Access to secretsline 113
```
[Credential-related source omitted]
```
Access to secretsline 115
```
[Credential-related source omitted]
```

Network accessline 140

if self._api_key.encode() in data:             raise JevError("request contains the API credential; refusing to send")         request = urllib.request.Request(ENDPOINT, data=data, headers={

Network accessline 141
```
[Credential-related source omitted]
```

Network accessline 142

request = urllib.request.Request(ENDPOINT, data=data, headers={

`agentfleet/otel.py`

Executable scriptline 1
```
Executable file
```

Network accessline 85

n_spans = len(payload["resourceSpans"][0]["scopeSpans"][0]["spans"])     if endpoint:         req = urllib.request.Request(

Network accessline 86

if endpoint:         req = urllib.request.Request(             endpoint.rstrip("/") + "/v1/traces",

Network accessline 87
```
req = urllib.request.Request(
```

Network accessline 90

headers={"Content-Type": "application/json"},         )         with urllib.request.urlopen(req) as resp:

Network accessline 91

)         with urllib.request.urlopen(req) as resp:             resp.read()

Network accessline 92

with urllib.request.urlopen(req) as resp:

`examples/demo.py`

Executable scriptline 1
```
Executable file
```

Network accessline 59

n = len(payload["resourceSpans"][0]["scopeSpans"][0]["spans"])     print(f"\notel export: {n} spans ready for a collector "           f"(pipe to Grafana with export-otel --endpoint http://localhost:4318)")

Network accessline 61

f"(pipe to Grafana with export-otel --endpoint http://localhost:4318)")

`tests/test_engine.py`

Executable scriptline 1
```
Executable file
```

`tests/test_jev.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 52
```
[Credential-related source omitted]
```
Access to secretsline 55
```
[Credential-related source omitted]
```
Access to secretsline 56
```
[Credential-related source omitted]
```

Network accessline 97

self.assertEqual(str(caught.exception), f"TypeSafe HTTP {code}; request not completed")             self.opener.open.assert_called_once()         self.assertIsNone(jev._NoRedirect().redirect_request(None, None, 302, "", {}, "https://untrust

Network accessline 99

self.assertIsNone(jev._NoRedirect().redirect_request(None, None, 302, "", {}, "https://untrusted.invalid"))

Access to secretsline 236
```
[Credential-related source omitted]
```
Access to secretsline 237
```
[Credential-related source omitted]
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 48 facts

Network access in prose of documentationREADME.md:10Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:12Low confidence
Network access in code of documentationREADME.md:34Low confidence
Network access in prose of documentationREADME.md:44Low confidence
Access to secrets in prose of documentationREADME.md:46Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.md:73Low confidence
Network access in code of documentationREADME.md:96Low confidence
Network access in prose of documentationREADME.md:101Low confidence
Access to secrets in prose of the SKILL.mdSKILL.md:40Low confidence
Executable script in code of a file that runsagentfleet/__init__.py:1High confidence
Executable script in prose of a file that runsagentfleet/cli.py:1Low confidence
Network access in prose of a file that runsagentfleet/cli.py:3Low confidence
Network access in prose of a file that runsagentfleet/cli.py:4Low confidence
Network access in prose of a file that runsagentfleet/cli.py:5Low confidence
Network access in prose of a file that runsagentfleet/cli.py:6Low confidence
Network access in prose of a file that runsagentfleet/cli.py:7Low confidence
Network access in code of a file that runsagentfleet/cli.py:17High confidence
Network access in code of a file that runsagentfleet/cli.py:18High confidence
Executable script in prose of a file that runsagentfleet/engine.py:1Low confidence
Executable script in prose of a file that runsagentfleet/jev.py:1Low confidence
Network access in code of a file that runsagentfleet/jev.py:9High confidence
Access to secrets in prose of a file that runsagentfleet/jev.py:106Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagentfleet/jev.py:112Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagentfleet/jev.py:113Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagentfleet/jev.py:115Low confidence
Network access in code of a file that runsagentfleet/jev.py:140High confidence
Network access in code of a file that runsagentfleet/jev.py:141High confidence
Network access in code of a file that runsagentfleet/jev.py:142High confidence
Executable script in prose of a file that runsagentfleet/otel.py:1Low confidence
Network access in code of a file that runsagentfleet/otel.py:85High confidence
Network access in code of a file that runsagentfleet/otel.py:86High confidence
Network access in code of a file that runsagentfleet/otel.py:87High confidence
Network access in code of a file that runsagentfleet/otel.py:90High confidence
Network access in code of a file that runsagentfleet/otel.py:91High confidence
Network access in code of a file that runsagentfleet/otel.py:92High confidence
Executable script in prose of a file that runsexamples/demo.py:1Low confidence
Network access in code of a file that runsexamples/demo.py:59High confidence
Network access in code of a file that runsexamples/demo.py:61High confidence
Executable script in prose of a testtests/test_engine.py:1Low confidence
Executable script in prose of a testtests/test_jev.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_jev.py:52Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_jev.py:55Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_jev.py:56Low confidence
Network access in code of a testtests/test_jev.py:97Low confidence
Network access in code of a testtests/test_jev.py:99Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_jev.py:236Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_jev.py:237Low confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

dreamers-laboratory/agent-fleet-manager

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

agent-fleet-manager

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.gitignore

LICENSE

README.md

SKILL.md

agentfleet/__init__.py

agentfleet/cli.py

agentfleet/engine.py

agentfleet/jev.py

agentfleet/otel.py

examples/demo.py

tests/test_engine.py

tests/test_jev.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

`SKILL.md`

`.gitignore`

`LICENSE`

`README.md`

`SKILL.md`

`agentfleet/init.py`

`agentfleet/cli.py`

`agentfleet/engine.py`

`agentfleet/jev.py`

`agentfleet/otel.py`

`examples/demo.py`

`tests/test_engine.py`

`tests/test_jev.py`