AgentSidekick

Background Agents

Scheduled and long-running agents that work unattended. As of 2026-11-21, 4 indexed products offer it (4 with full profiles), in 2 forms: 3 MCP servers, 1 Agent skill. 1 were published in the last 90 days, against 1 in the 90 days before. zenith has the most GitHub stars, 95% of the total across 3 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Little here yet. Only 4 products with a full profile match this capability (4 in the whole catalogue). Matching is by the keywords listed below, so products that do this without using those words are missed. The page is kept for navigation and is not offered to search engines until at least 5 profiled products match. A low count is not proof that anyone wants this.

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 3 indexed · 3 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Background Agents: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1zenithZenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.Intelligent-Internet4042mo ago
2offloadHand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.tailucanh2311d ago
3eventsorg-mcpAutonomous MCP server and background agent for managing live event logistics.guth0101mo ago

Agent skills 1 indexed · 1 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Background Agents: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1autoresearchAutonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy''s autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.github—1d ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code1
Codex1
Google Antigravity1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

No integrations named

None of the products matched here names a tracked third-party service.

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
background agent2
scheduled agent0
cron agent0
long-running agent1
async agent0
autonomous loop1

Segment statistics

Whole catalogue (4 indexed products). Calculated 2026-11-21.

4DERIndexed products4 with full profiles
1DERLaunched, last 90 days1 in the 90 days before
UnknownDERMomentum vs catalogueFewer than 5 dated launches in 180 days
95%DERLargest project's share of starsAcross 3 products with their own repository
0.898DERConcentration (HHI)About 1 equal-sized projects’ worth; highly concentrated
23SRCMedian starsPer product with its own repository
100%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.898 means stars are spread as if across about 1 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: Background Agents: score 59.1 HEU, competition Medium, confidence Low. Only 4 indexed products match "Background Agents", against 631 in Agent Deployment overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .