SageZHangZHengEric/Sage
[Core Features]: An RSI agent harness that starts from a goal or curated usage history: a Runner executes,…
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/ZHangZHengEric/Sage.git
OverviewOverview
[Core Features]: An RSI agent harness that starts from a goal or curated usage history: a Runner executes, an independent Evaluator grades, a Tuner optimizes, and every version with its evidence is retained while adoption stays with the user. It supports models and context, skills and MCP, stateful execution, multi-agent workflows, sandboxes and approvals across multiple hosts; version 2.2 adds desktop plugins, macOS, Windows and Linux builds, a web server package and a Python SDK. [Applicable Scenarios]: Agent evaluation, recursive self-improvement, multi-agent orchestration and version evidence. [Target Roles]: AI engineer, agent developer and evaluation researcher.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 5992 |
|---|---|
| Data source | GitHub |
| Repository | ZHangZHengEric/Sage |
| Category | AI & Agent Skills / Recursive Self-Improvement Agent Harness |
| Primary language | Not specified |
| License | Not specified |
| Default branch | |
| GitHub repository ID | |
| Rank | #744 (position within the source ranking) |
| Site-wide popularity rank | #851 (computed live from Stars, across all 5893 entries) |
GrowthStar / Fork growth
TimelineTimeline
CommitLatest commit
New Feature: Avoid re-encoding large Sage v2 raw trace snapshots