Show HN: Coding agent with algebraic memory (VSA) instead of RAG
Raidho is an open‑source coding agent that separates reasoning and execution across different language models. It uses a durable algebraic memory based on Vector Symbolic Architecture instead of traditional retrieval‑augmented generation. The design aims to reduce costs by allocating expensive models to planning and cheap models to code execution, and it supports multiple providers via API keys.
- ▪Raidho splits tasks between a high‑cost reasoning model (e.g., Claude) and a low‑cost execution model (e.g., DeepSeek).
- ▪The agent stores subject‑relation‑object facts in a VSA memory that persists across runs and can be recalled without re‑loading full histories.
- ▪Benchmark tests show the hybrid approach can achieve comparable quality to a pure tool‑loop at roughly one‑third of the cost.
- ▪The system is provider‑agnostic, allowing users to plug in Claude, DeepSeek, OpenAI‑compatible endpoints, or custom embeddings via simple configuration.
- ▪Raidho is released in alpha, with a lightweight codebase that depends only on numpy and can be installed via pip or an interactive script.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/vitaliyfedotovpro-art/raidho |
| Publication time | Sun, 14 Jun 2026 23:44:56 +0000 |
| Retrieval time | 2026-06-15T00:07:33.547Z |
| Last seen | 2026-06-15T00:07:33.547Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | dQl6wCAxR65E |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Raidho ᚱ A coding agent that plans with one model, executes with another, and remembers what it learns. Most coding agents are one model in a tool loop. Raidho splits the work: use a smart, expensive model to reason and plan, a cheap, fast model to execute, and a durable memory that carries facts across runs — all provider-agnostic, with your own API key. The name is the rune Raidho (ᚱ) — "journey / movement". Status: alpha. Tested end-to-end live against both backends (DeepSeek and Claude through the official Anthropic SDK, including the agentic tool-loop).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.