~/pushd/gh$pushd read SalvorLabs/Salvoron the list

SalvorLabs/Salvor

Repo-owned engineering memory for coding agents - preserve decisions, failures, domain knowledge, and deferred work across sessions, teams, and models.

ShellMIT AI agentsagentic-aicoding-agentsdeveloper-productivitydeveloper-toolsengineering-memoryllm
stars
12
forks
4
watchers
0
open issues
35
created
22 Jun 2026
last push
36d ago
GitHub ->Site ->Read from GitHub just now.

README

the first lines
A repo-native engineering knowledge layer for coding agents and software teams. [](https://github.com/dwasyluk/salvor/releases) [](./LICENSE) [](./docs/VENDOR_ADAPTERS.md) [](./CONTRIBUTING.md) *Git preserves what changed. Salvor preserves what the project learned.* ## The engineering problem The models are getting very good at coding. Re-teaching every fresh session what the project already learned is still a terrible engineering workflow. A new agent can inspect functions, dependencies, commits, and tests. It can still miss that a plausible approach failed three sessions ago, an odd-looking implementation protects a vendor quirk, an architectural constraint must survive the next refactor, or a teammate already investigated the same issue.

Ask a scout

a deep read
GeminiGoogle . Gemini 3.8 Flash for the deep read

SalvorLabs is in the AI agents camp, which Gemini reads.

10 of 10 public reads left today. Holders get 3 a day.
No read kept yet.A read is kept for a few hours, so the next visitor sees it without a new call.

Scout calls and heat are information, not advice. They describe public GitHub activity and are never a signal to trade.