Skip to content

Catalogagents

Singular

situationalBlueshift — gaining momentum

Autonomous multi-agent orchestration engine that runs coding agents in parallel against a repo.

Visit github.com →Add to kitOpen in Noemium

ledger entry · observed by @whysanesanders

Brings git-worktree isolation, durable leases, and a three-tier scheduler to long-running agent workflows. It is engineered for teams that want many autonomous coding agents working on the same repo without stepping on each other. Setup is nontrivial and the documentation assumes you already run Claude Code or Codex.

Strengths

  • Git-worktree isolation, durable leases and a three-tier scheduler for agent workflows.
  • Lets multiple autonomous coding agents work the same repo without collisions.
  • GPL-3.0 open source and self-hostable on your own runner.

Known limitations

  • Requires bash 4+, Python, git, and a supported runner CLI already configured.
  • Engine must be installed from a checkout; there is no download mechanism for the pinned engine.
  • The default promoter is minimal, so real workflows need custom gate and promoter scripts.

Use it when

  • Teams running multiple long-lived coding agents against one repository.
  • Shops already using Claude Code or Codex and wanting isolation and scheduling.

Skip it when

  • You cannot install from source or configure a supported runner CLI.
  • Your workflows need a polished default promoter out of the box.
  • You lack the engineering time for nontrivial setup and custom gate scripts.

Buy-check

  • ·Price — free, GPL-3.0 open source; bring your own runner (Claude Code, Codex, etc.) as of 2026-08-19. Open the pricing page, not a screenshot.
  • ·Free tier — Free tier exists — burn it first.
  • ·Cancel fallout — What happens to your data/projects on cancel — check the ToS, not the FAQ.
  • ·Seat math — Per-seat pricing multiplies quietly. Count seats before the annual plan.
  • ·Who skips it — Also skipped when: You cannot install from source or configure a supported runner CLI.; Your workflows need a polished default promoter out of the box..

Price trailchangelog →

No price move in this repo yet.

Facts

pricing
free1
price note
GPL-3.0 open source; bring your own runner (Claude Code, Codex, etc.)
free tier
yes
open source
yes
api
no
self-host
yes
category
agents
evidence
source-verified

Data: trains on inputs unknown · local processing yes

Sources

  1. 1github.com/alex-reysa/singular-lite[snapshot]
  2. 2github.com/alex-reysa/singular-lite/blob/main/LICENSE[snapshot]

No source, no number.

Edit this page on GitHub

Similar joball alternatives →

Compare:Singular vs CrewAI

toolverdictpriceossself-host
Singularsituationalfreeyesyes
Difyshipfreemiumnoyes
CrewAIshipfreemiumyesyes
LangGraphshipfreemiumyesyes

Facts from the catalog files — not scores you can buy. Quality and speed stay in the briefing, not in a fake 1–5 grid.

Dify
agentsship

Dify

Source-available LLM app platform with agent workflows and RAG.

APIFREE TIER

freemiumCloud Sandbox free; self-host Community free under restricted license; cloud Professional/Team paid yearly

Blueshift — gaining momentum
CrewAI
agentsship

CrewAI

Python framework for multi-agent crews — roles, tasks and processes.

OSSAPIFREE TIER

freemiumopen source (MIT); cloud Free Basic (50 exec/mo); Enterprise custom

Steady momentum
LangGraph
agentsship

LangGraph

Graph-based agent orchestration from LangChain — stateful and controllable.

OSSAPIFREE TIER

freemiumframework free open-source; LangSmith Plus $39/seat/mo

Blueshift — gaining momentum