Skip to content
Projects

Alpha-Park/genpark-agent-continuous-context-session-compactor-skill

View on GitHub

Alpha-Park/genpark-agent-continuous-context-session-compactor-skill has 0 GitHub stars and 0 forks. GitHot measured 0 in 7 days. Last checked 2026-11-10 19:23 UTC. Last push 2026-10-30.

How these counts are measured

Continuous long-context conversation compactor tracking token budgets, generating condensed sliding history summaries, and preventing context window truncation

0 stars0 forks

What you can do

  • Token Budget Guarding: Enforces strict configurable budget limits (e.g. 8k, 32k, 128k).
  • Sliding History Distillation: Preserves critical system instructions and recent conversation while compressing historical turns.
  • Zero Overhead: In-memory token estimation and distillation with zero external LLM dependencies.

Measured star growth

in 24h
Update delayed
in 7 days
0
in 15 days
Update delayed
in 1 month
Update delayed

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

README.md

Original

Continuous Context Session Compactor Skill for Autonomous Agents

MCP Compatible Python 3.9+ License: MIT Zero External Dependencies

Enables long-horizon autonomous agents to run persistently without context window exhaustion. Automatically calculates token consumption and creates concise sliding summaries for elder turns.

Capabilities

  • Token Budget Guarding: Enforces strict configurable budget limits (e.g. 8k, 32k, 128k).
  • Sliding History Distillation: Preserves critical system instructions and recent conversation while compressing historical turns.
  • Zero Overhead: In-memory token estimation and distillation with zero external LLM dependencies.

MCP Server Integration

python mcp_server.py

Available MCP Tools

  • compact_messages: Compact conversation array when exceeding token limits.

Explore related projects

affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

300,970 stars

NousResearch/hermes-agent

The agent that grows with you

262,559 stars

multica-ai/andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

232,009 stars

firecrawl/firecrawl

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

200,444 stars