Decispher – persistent engineering context and memory for coding agents
Hello HN, I'm Ali, building Decispher. The problem we're working on is that coding agents repeatedly rediscover context that already exists inside an engineering organization. A developer working on a feature can combine information from previous PRs, Jira tickets, Slack discussions, ownership boundaries, architectural decisions and their own experience. Coding agents usually start with a prompt and a repository, then spend tokens searching for that same context—or miss it entirely. Decispher is a context and memory layer for engineering agents. It currently has three parts: 1) Context…
What it does
In the maker’s words, at launch
Hello HN, I'm Ali, building Decispher. The problem we're working on is that coding agents repeatedly rediscover context that already exists inside an engineering organization. A developer working on a feature can combine information from previous PRs, Jira tickets, Slack discussions, ownership boundaries, architectural decisions and their own experience. Coding agents usually start with a prompt and a repository, then spend tokens searching for that same context—or miss it entirely. Decispher is a context and memory layer for engineering agents. It currently has three parts: 1) Context Engine Engineering context is usually fragmented across systems. Decispher connects records from engineering platforms and combines related fragments into context units that agents can retrieve for a task. For example, context around a component might include previous PRs, related issues, architectural decisions, ownership information and implementation history. We also built Branch Story, which records an AI coding session and turns its execution into a structured handoff on the PR: Prompt → plan → actions → result. 2) Memory Plane The Memory Plane stores persistent context at the user, team and project levels. This includes working preferences and engineering conventions. Teams can also create reusable memory sets for example frontend, payments-backend, or project-specific sets and inject the relevant memory based on the task. On LongMemEval, our current system reaches: a) 89% accuracy on the oracle split using GPT-4.1-mini as extractor and reader b) 81% on LongMemEval -S dataset (89% with frontier models) c) 38× median token reduction I'm happy to share more details about how we measure retrieval quality and token reduction. 3) Worker Agent Decispher also has an autonomous worker agent that uses the Context Engine and Memory Plane while working on a task. It can take work from sources such as Jira and Slack, retrieve relevant context and ownership information, and ask the humans involved when the available context is insufficient instead of guessing. Those answers can then become available as context for future work. The Context Engine, Memory Plane and Worker Agent can be used independently. Setup npx decispher init This connects a repository and configures the agent integration. npx decispher link This links your decispher account to your repo. Decispher works with MCP compatible agents, with specific integrations for Claude, Codex, Grok Build and Cursor. We also have a VS Code/OpenVSX extension for viewing context and writing handoffs. Notes: a) The Context Engine does not clone source code; it reads and writes through the GitHub API. b) The Worker Agent uses an isolated sandbox with no network route out except through an allowlisted proxy. c) Worker sandboxes are destroyed after a run. d) Raw messages and text are encrypted at rest and automatically purged. Sessions are currently purged 7 days after merge or 30 days after last activity, with configurable retention. We also have an MIT-licensed open-source project called Decision Guardian for surfacing ADR context on PRs. The Context Engine is available now. Memory and the Worker Agent are rolling out gradually. I'm especially interested in feedback and we are also looking for design partners. Happy to answer. Ali This is a follow-up to my previous Show HN post: https://news.ycombinator.com/item?id=48762112 The major additions since then are the Memory Plane, LongMemEval results, Worker Agent sandboxing and Branch Story for AI-generated work on PRs.
Does the same job
all alternatives →
Decispher Memory4d ago · decispher.com · ▲10Memory for coding agents that learns how your team works
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com