context-window repositories
Trending repositories tagged context-window, ranked by trending score. Updated daily.
-
1
headroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
GitHub · Python · 80,214 stars · 6,287 forks · +115 stars in 24 hours · Trending score 4.15
-
2
scasella/claude-flightdeck
A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.
GitHub · TypeScript · 334 stars · 52 forks · +77 stars in 24 hours · Trending score 3.28
-
3
yuhuan-dev/antigravity-usage-monitor
Real-time Google Antigravity monitor for token usage, context windows, quotas, generation speed (TPS), TTFT and subagent analytics.
GitHub · JavaScript · 92 stars · 22 forks · +24 stars in 24 hours · Trending score 2.87
-
4
localixai/tokendoctor
tokendoctor: the same Claude Code for up to 38% less. Replays your own past sessions to show what each change would have saved, then changes only what you pick
GitHub · TypeScript · 170 stars · 12 forks · +17 stars in 24 hours · Trending score 2.58
-
5
toprakahmetaydogmus/TZeroAlgorithm
Deterministic AST Context Compressor & MCP Server for Cursor, Claude & Local LLMs. Cuts prompt tokens by 85–95% with 100% Zero-Leak security.
GitHub · Python · 45 stars · 1 forks · +13 stars in 24 hours · Trending score 2.10
-
6
Lumidarin/agy-capsule
Context usage, model quotas, token breakdowns, and generation metrics — right in your Antigravity composer.
GitHub · JavaScript · 133 stars · 6 forks · +35 stars in 24 hours · Trending score 1.74
-
7
lastreload/mnemonic-proxy
Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.
GitHub · Python · 80 stars · 7 forks · +8 stars in 24 hours · Trending score 1.73
-
8
mnemon-dev/mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
GitHub · Go · 724 stars · 83 forks · +5 stars in 24 hours · Trending score 1.66
-
9
inevolin/claude-code-usage-analysis
Empirical analysis of Claude Code token usage: auto-compaction sweet spots across 8 developer workflows and Claude Desktop vs. CLI overhead
GitHub · Python · 137 stars · 5 forks · +31 stars in 24 hours · Trending score 1.66
-
10
redhat-et/ripwire
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
GitHub · C++ · 2,557 stars · 179 forks · +4 stars in 24 hours · Trending score 1.62
-
11
zzet/gortex
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
GitHub · Go · 2,090 stars · 207 forks · +3 stars in 24 hours · Trending score 1.53
-
12
smart-mcp-proxy/mcpproxy-go
Supercharge AI Agents, Safely
GitHub · Go · 427 stars · 75 forks · +2 stars in 24 hours · Trending score 1.36
-
13
wycocoyu/agy-context-dashboard
Antigravity (agy) context window, token usage, cache hit & quota dashboard — community fork of antigrative-dashboard (antigravity-pulse, MIT).
GitHub · JavaScript · 74 stars · 7 forks · +12 stars in 24 hours · Trending score 1.26
-
14
NodeNestor/claude-rolling-context
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.
GitHub · Python · 34 stars · 9 forks · +3 stars in 24 hours · Trending score 1.06
-
15
MikeGT4/agent-tree
Terminal side pane for Claude Code that shows a session's agents as a live tree, with tabs for full reports, files, log and usage. Stop a running sub-agent, send it new instructions mid-task, switch its model by click, customize the look. Works in Code Mode. Updates itself and shows what is new.
GitHub · TypeScript · 23 stars · 2 forks · +2 stars in 24 hours · Trending score 0.96
-
16
duqaXxX/seedeep
What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.
GitHub · TypeScript · 49 stars · 3 forks · +3 stars in 24 hours · Trending score 0.91
-
17
jgravelle/jcodemunch-mcp
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
GitHub · Python · 2,858 stars · 377 forks · 0 stars in 24 hours · Trending score 0.90
-
18
tokensafe-dev/tokensafe
Your AI agent is smart enough to code all day. Now it actually can. Local runtime firewall & zero-loss context optimizer for AI coding agents.
GitHub · Python · 47 stars · 2 forks · +1 stars in 24 hours · Trending score 0.87
-
19
akelabs/antigravity-pulse
Live tok/s and context-capacity capsule beside Turbo in Google Antigravity 2.0
GitHub · 53 stars · 4 forks · +4 stars in 24 hours · Trending score 0.80
-
20
reshaprio/reshapr
The open source runtime that turns your APIs AI-Native, without rebuilding them
GitHub · Java · 180 stars · 40 forks · +1 stars in 24 hours · Trending score 0.77
-
21
thousandflowers/skillreaper
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
GitHub · Go · 66 stars · 8 forks · 0 stars in 24 hours · Trending score 0.75
-
22
archid21/rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
GitHub · TypeScript · 46 stars · 13 forks · +3 stars in 24 hours · Trending score 0.72
-
23
Spobi/context-carwash
Context Carwash: ⟡ see your full session context size at all times ⟡ /clear with no worries about loosing context or adding to your file bloat ⟡ specify the exact context you want saved for the next session
GitHub · JavaScript · 30 stars · 1 forks · 0 stars in 24 hours · Trending score 0.72
-
24
Locotir/nexo
Terminal coding agent in Rust for any provider; its context curator keeps long sessions small without summaries
GitHub · Rust · 8 stars · 0 forks · +1 stars in 24 hours · Trending score 0.70