Show HN: Elpis – a Rust TUI for LLM agents with context pruning
Elpis Your terminal agent forgets everything. Every coding agent today has the same disease: the longer you work, the worse it gets. Every new session starts with you explaining your task again, and every model request resends an ever-fatter history you're paying for.
- ▪Elpis Your terminal agent forgets everything.
- ▪Every coding agent today has the same disease: the longer you work, the worse it gets.
- ▪Every new session starts with you explaining your task again, and every model request resends an ever-fatter history you're paying for.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,266 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/MasihMoafi/Elpis |
| Publication time | Thu, 23 Jul 2026 07:20:16 +0000 |
| Retrieval time | 2026-07-23T08:18:15.518Z |
| Last seen | 2026-07-23T08:18:15.518Z |
| 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 | 6qo0S4LuHiTT |
| 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
Elpis Your terminal agent forgets everything. Elpis doesn't. Every coding agent today has the same disease: the longer you work, the worse it gets. Goals drown in transcripts. Decisions vanish at compaction. Every new session starts with you explaining your task again, and every model request resends an ever-fatter history you're paying for. Elpis is a terminal agent shell that treats context as a managed asset, not an ever-growing log: Post-turn context pruning. After a turn delivers its answer, raw exploration — command dumps, file reads, failed probes — is replaced in the next request by compact receipts with exact evidence pointers. The full transcript stays on disk, retrievable on demand; it just stops being resent by default. No other open agent does this per-turn.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.