The intelligent execution layer for AI agents — CLI interface
Project description
Keshro
Make AI agents execute intelligently. Structured plans, parallel execution, cross-task learning.
pip install keshro
keshro login <token> # from keshro.com/account
keshro create # scan project, generate plan
keshro continue --all # agents execute in parallel
The problem
Your AI agent is great at one task at a time. But real projects have 10-20 tasks with dependencies, shared context, and files that shouldn't be edited by two agents at once.
Run them manually and you're the bottleneck. Run them in parallel and they conflict.
What Keshro does
- Plans the work — generates a dependency graph with task ordering, file assignments, acceptance criteria, and risk flags
- Runs agents in parallel — each in an isolated git worktree, respecting dependency order
- Shares context across tasks — when one agent discovers something, related future tasks inherit that knowledge
- Tracks everything — git checkpoints before each task, decision audit trails, one-command rollback
Create from anything
keshro create # current directory
keshro create https://github.com/org/repo # GitHub repo
keshro create https://github.com/org/repo/issues/42 # GitHub issue
keshro create https://linear.app/team/issue/PROJ-123 # Linear issue
Your AI agent scans the project, answers clarifying questions, and generates the plan.
Execute
Keshro drives the full execution loop — picks up the next task, gives the agent context, validates the result, marks it done, and moves to the next one. You don't manage it.
keshro continue # execute next task, then the next, then the next
keshro continue --all # run everything — parallel agents, each in its own worktree
keshro continue --all -c 10 # cap at 10 concurrent agents
keshro continue --dry-run # preview what would run
Monitor
keshro status # progress summary
keshro status --tui # live terminal dashboard
keshro explain <task-id> # decision audit trail
keshro rollback <task-id> # revert to pre-task state
Works with
Claude Code, Codex, Cursor, Devin, or any AI agent that runs in a terminal.
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file keshro-0.1.3.tar.gz.
File metadata
- Download URL: keshro-0.1.3.tar.gz
- Upload date:
- Size: 75.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8f45b28317434bf0be70e7662841aa8a4815d57d2f9e403aa40550bfe1860024
|
|
| MD5 |
17df35dfc0dbf45b53b04ddbe4315d61
|
|
| BLAKE2b-256 |
ffe5a3f97e1ce59d45265abfe2e9e1fbcca8af9e4faace3b2202caa80d5aadfb
|
Provenance
The following attestation bundles were made for keshro-0.1.3.tar.gz:
Publisher:
publish.yml on jlewitt1/keshro-cli
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
keshro-0.1.3.tar.gz -
Subject digest:
8f45b28317434bf0be70e7662841aa8a4815d57d2f9e403aa40550bfe1860024 - Sigstore transparency entry: 1193955544
- Sigstore integration time:
-
Permalink:
jlewitt1/keshro-cli@1d42513d787710b06bb857bdfc5d894078a178b0 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/jlewitt1
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@1d42513d787710b06bb857bdfc5d894078a178b0 -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file keshro-0.1.3-py3-none-any.whl.
File metadata
- Download URL: keshro-0.1.3-py3-none-any.whl
- Upload date:
- Size: 63.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3a41257afdd7a4b39af3a004c704c4f7c4174040d74e8ef9ae454977429b514e
|
|
| MD5 |
e42f5355e772084240348fd3d1e7138a
|
|
| BLAKE2b-256 |
cc10e605791ce74caba4745f2e1bb3c988f3bdecc8a4c40845037570446c319f
|
Provenance
The following attestation bundles were made for keshro-0.1.3-py3-none-any.whl:
Publisher:
publish.yml on jlewitt1/keshro-cli
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
keshro-0.1.3-py3-none-any.whl -
Subject digest:
3a41257afdd7a4b39af3a004c704c4f7c4174040d74e8ef9ae454977429b514e - Sigstore transparency entry: 1193955563
- Sigstore integration time:
-
Permalink:
jlewitt1/keshro-cli@1d42513d787710b06bb857bdfc5d894078a178b0 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/jlewitt1
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@1d42513d787710b06bb857bdfc5d894078a178b0 -
Trigger Event:
workflow_dispatch
-
Statement type: