Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message
| Date | Stars |
|---|---|
| 2026-07-31 | 922 |
| 2026-08-05 | 959 |
| 2026-08-06 | 959 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<p align="center"> <img src="docs/banner.png" alt="HERMES-LCM" width="800"> </p> [](https://github.com/stephenschoettler/hermes-lcm/actions/workflows/ci.yml) [](https://github.com/stephenschoettler/hermes-lcm/releases) [](https://github.com/stephenschoettler/hermes-lcm/actions/workflows/ci.yml) [](LICENSE) **Lossless Context Management plugin for [Hermes Agent](https://github.com/NousResearch/hermes-agent).** > Bounded context, unbounded memory. Nothing is ever lost. `hermes-lcm` replaces one-shot active-context compression with a SQLite-backed, DAG-based context engine. It keeps the live prompt bounded, preserves raw messages, and gives the agent tools to recover exact detail after compaction. Based on the [LCM paper](https://papers.voltropy.com/LCM) by Ehrlich & Blackman (Voltropy PBC, Feb 2026). Inspired by [lossless-claw](https://github.com/martian-engineering/lossless-claw) for OpenClaw. For an interactive visualization of the LCM idea, see [losslesscontext.ai](https://losslesscontext.ai/). ## Table of contents - [What it does](#what-it-does) - [LCM vs built-in compression](#lcm-vs-built-in-compression) - [Quick start](#quick-start) - [Commands and tools](#commands-and-tools) - [Recall skill and policy](#recall-skill-and-policy) - [Configuration](#configuration) - [Retrieval contract](#retrieval-contract) - [OpenClaw/lossless-claw import](#openclawlossless-claw-import) - [Troubleshooting](#troubleshooting) - [Architecture](#architecture) - [How it works](#how-it-works) - [Documentation](#documentation) - [Development](#development) - [Contributing](#contributing) - [License](#license) ## What it does Hermes Agent's built-in compressor is a practical continuity layer: when the prompt crosses its configured threshold, it prunes older tool results, asks an auxiliary model to summarize the middle/older conversation, and rebuilds the active prompt from that summary plus a protected recent tail. The original session rows can still live in Hermes `state.db` and remain searchable through host tools such as `session_search`, but the model's active context no longer contains the compacted turns verbatim or a structured drill-down path back to them. `hermes-lcm` instead: 1. **Persists messages** in a plugin-local SQLite store with FTS metadata. 2. **Compacts older context** into depth-aware summary nodes. 3. **Condenses summaries** into a hierarchical DAG as they accumulate. 4. **Assembles active context** from system prompt, highest-value summaries, and the protected fresh tail. 5. **Provides recall tools** so agents can search, inspect, and expand compacted material without flooding the main prompt. Nothing is lost in normal operation. Raw messages stay recoverable in bounded pages, summaries retain source lineage, and oversized externalized payloads keep stable refs for later expansion. <p align="center"> <img src="docs/standard_compression.png" alt="Standard compression" width="700"> </p> <p align="center"> <img src="docs/lcm_compression.png" alt="LCM compression" width="700"> </p> Core capabilities: - **SQLite message store** - preserves raw messages before compaction - **Summary DAG** - builds depth-aware summary nodes over compacted history - **Bounded recovery** - pages raw messages, child summaries, and externalized payloads instead of dumping everything into the prompt - **Agent tools** - `lcm_grep`, `lcm_recall`, `lcm_query_state`, `lcm_compute`, `lcm_compile_evidence`, `lcm_evidence_pack`, `lcm_retrieve`, `lcm_recent`, `lcm_load_session`, `lcm_describe`, `lcm_expand`, `lcm_expand_query`, `lcm_status`, `lcm_inspect`, and `lcm_doctor` - **Source-aware retri
Excerpt of 43,625 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:edb1c107e47a8a14, llm:Description: 'Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message' (repo description). Language: Python.
matched fp:edb1c107e47a8a14, llm:Description: 'Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message' (repo description). Language: Python.
