trajectory

About trajectory

trajectory Normalize agent transcripts from different runtimes into one validated, model-ready record format. Agent tools represent the same concepts—messages, reasoning, tool calls, and tool results—in incompatible native formats. provides one TypeScript API that turns those formats into deterministic, structured records for training, evaluation, analysis, and inference. The caller supplies a transcript string and its source. The one exception is Deep Agents, whose sessions reads from its local LangGraph SQLite store by thread ID; see .

agent-harness agent-memory claude-code codex deepagents dreaming hermes-agent openclaw openhands

Quick Facts

Stars	263
Forks	24
Language	TypeScript
Category	Codex Skill
License	Apache-2.0
Quality Score	38.25/100
Open Issues	10
Last Updated	2026-09-25
Created	2026-07-10
Platforms	claude-code, codex, node
Est. Tokens	~38k

Compatible Skills

These tools work well together with trajectory for enhanced workflows:

metaharness — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (56%)
agent-harness-generator — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (56%)
memX — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)
Zleap-Agent — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)
memorix — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

More Codex Skill Tools

Explore other popular codex skill tools:

openclaw ⭐ 392.8k
hermes-agent ⭐ 256.1k
ui-ux-pro-max-skill ⭐ 138.5k
agent-skills ⭐ 106.3k
orca ⭐ 102.3k
open-design ⭐ 102.0k
taste-skill ⭐ 99.9k
graphify ⭐ 76.9k
career-ops ⭐ 76.5k
system_prompts_leaks ⭐ 69.9k

View all Codex Skill tools →

Popular TypeScript Agent Tools

openclaw ⭐ 392.8k · Codex Skill
rea ⭐ 362.8k · MCP Server
n8n ⭐ 208.3k · MCP Server
claude-code ⭐ 151.8k · Agent Tool
gemini-cli ⭐ 107.5k · MCP Server

Frequently Asked Questions

What is trajectory?

trajectory is Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search). It is categorized as a Codex Skill with 263 GitHub stars.

What programming language is trajectory written in?

trajectory is primarily written in TypeScript. It covers topics such as agent-harness, agent-memory, claude-code.

How do I install or use trajectory?

You can find installation instructions and usage details in the trajectory GitHub repository at github.com/letta-ai/trajectory. The project has 263 stars and 24 forks, indicating an active community.

What license does trajectory use?

trajectory is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Codex Skill tools