Alternatives
Products that do what Context-compact – Summarize agent context instead of truncating it does
agents. Not a custom truncation strategy, not a sliding window, not dropping old messages and hoping for the best. The failure mode is well-understood: your context window fills up, you truncate from the top, and the agent loses the thread. It forgets the task it was working on, the file path it just wrote to, the UUID it needs to reference. The conversation breaks. The problem is everyone keeps solving it by throwing away information instead. Truncation is fast to implement and quietly wrong. The agent appears to work until it doesn't, and debugging context loss in a long-running session is…
- 1
- 2
- 3CS
AI agents accumulate stale tool results — file reads, web fetches, bash outputs — in their context window. Every one sits there for the entire conversation, consuming tokens and degrading quality. The standard fix is auto-compaction: wait until full, then drop content indiscriminately. Context Surgeon gives the agent three operations — evict, replace, and restore — so it can manage its own context. It works as a transparent local proxy that intercepts API requests, assigns IDs to content blocks, and applies eviction directives before forwarding. The agent calls the tools via bash. The proxy…
Apr 2026 · github.com
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17UM
I was frustrated that memory is usually tied to a specific tool. They’re useful inside one session but I have to re-explain the same things when I switch tools or sessions. Furthermore, most agents' memory systems just append to a markdown file and dump the whole thing into context. Eventually, it's full of irrelevant information that wastes tokens. So I built this local memory layer that unifies memory across agents. Instead of a flat file, it builds a structured knowledge graph of "memory notes" inspired by the paper "A-MEM: Agentic Memory for LLM Agents"…
Apr 2026 · github.com
- 18LP
I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that minimizes how often long lived conversation history gets modified while still supporting dynamic context. It has flexible hooks for doing things like truncating or summarizing tool outputs when transitioning messages to the long term history. And I'm seeing >>90% of tokens hitting the cache for my agents despite including a lot of dynamic user context. There are a wide range of agent prompting strategies so I'd love to hear where this library…
Jun 2026 · github.com
- 19OS
Hello HN, I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem). To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills. The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers: Layer 1 (Metadata): Light-weight tags and triggers (always loaded…
Jan 2026
- 20CP
CoreMem lets you build collections of context, called a mem, and share it with any AI agent via URL, a Chrome extension, MCP, Cursor/VS Code plugins, a skill, and more. Instead of re-explaining your project or goal when you switch agents or start new sessions, CoreMem keeps your context centrally organized so that any AI tool can read it. This originally started as a CLI I built that kept pieces of context (Project A/B/C details, my writing style, preferred tech stacks, coding style, etc) in a SQLite database. I could instruct various agents to “use my `coremem` CLI to…
May 2026 · coremem.app
- 21MA
Most multi-agent systems fail the same way: agents drift apart across handoffs. By turn 3 they are working in different realities. By turn 5 they are repeating each other's mistakes and calling it parallelism. WUPHF is an open-source local-first office where AI coworkers run on your laptop, around a shared markdown + git LLM wiki the agents build. The wiki is the collective memory. The office around it keeps the team on the same shared context across thousands of handoffs. What actually stops drift is not the wiki. It is the agents reviewing each other's work. The CRO catching the CMO's…
May 2026 · wuphf.team
- 22RM
recursive-mode is an installable skill package for coding agents. It gives your agent a file-backed workflow for requirements, planning, implementation, testing, review, closeout, and memory, instead of leaving the whole process scattered in context. Long-running agent work has a common failure mode: requirements, decisions, and plans live in the conversation. Once the session ends or the context window overflows, the agent loses track of what was decided, what was implemented, and why. recursive-mode solves context rot by making repository documents the source of truth for every phase.…
Apr 2026 · recursive-mode.dev
- 23DE
I wanted a very simple way to dump prompts, links, and todo lists into my claude code and codex agents. And to work outside of the context window. This works particularly well for sharing "Projects" between Claude/ChatGPT etc. It's open source here; https://github.com/Vochsel/dump.page Anything you dump on the board becomes an llms.txt - spatially sorted implicitly and explicity sorted via connection edges. Would love HN's thoughts!
Mar 2026 · dump.page
- 24CS
I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of defensive spaghetti just to stop models from drifting. The problem is treating chat history as project state. A conversation is not a ledger. Castra is a compiled Go binary that strips orchestration rights from the LLM. State lives in an encrypted, local SQLite database (castra.db). The LLM is just a stateless executor — it reads the DB, executes a highly constrained task, and the result is written back subject to…
Apr 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →